Daily Papers

Sparse Autoencoders (SAEs) have been seen as a promising avenue for exploring the internals of Large Language Models (LLMs) and for steering model output generation. When AxBench - a model steering benchmark - was introduced in Wu et al. (2025), SAEs did not seem to live up to their original hype due to poor steering performance relative to a set of simple baselines. This work serves as a partial rebuttal for Sparse Autoencoders and suggests that the results of Wu et al. (2025) did not do them full justice. We find that Sparse Autoencoders can, in fact, perform close to on par with the reference LoRA performance on the AxBench benchmark, when features are selected and labelled with our supervised pipeline. We also find that our pipeline selects features that are surprisingly causal of their identified labels when using only its interpretability-based components. Lastly, we present evidence that high sparsity (low l0) may not be crucial for successful steering based on interpretability, which is in contrast to the earlier findings in Wang et al. (2025).

With growing abilities of generative models, artificial content detection becomes an increasingly important and difficult task. However, all popular approaches to this problem suffer from poor generalization across domains and generative models. In this work, we focus on the robustness of AI-generated image (AIGI) detectors. We analyze existing state-of-the-art AIGI detection methods based on frozen CLIP embeddings and show how to interpret them, shedding light on how images produced by various AI generators differ from real ones. Next we propose two ways to improve robustness: based on removing harmful components of the embedding vector and based on selecting the best performing attention heads in the image encoder model. Our methods increase the mean out-of-distribution (OOD) classification score by up to 6% for cross-model transfer. We also propose a new dataset for AIGI detection and use it in our evaluation; we believe this dataset will help boost further research. The dataset and code are provided as a supplement.

Ensuring faithful interpretability in large language models is imperative for trustworthy and reliable AI. A key obstacle is self-repair, a phenomenon where networks compensate for reduced signal in one component by amplifying others, masking the true importance of the ablated component. While prior work attributes self-repair to layer normalization and back-up components that compensate for ablated components, we identify a novel form occurring within the attention mechanism, where softmax redistribution conceals the influence of important attention scores. This leads traditional ablation and gradient-based methods to underestimate the significance of all components contributing to these attention scores. We introduce Gradient Interaction Modifications (GIM), a technique that accounts for self-repair during backpropagation. Extensive experiments across multiple large language models (Gemma 2B/9B, LLAMA 1B/3B/8B, Qwen 1.5B/3B) and diverse tasks demonstrate that GIM significantly improves faithfulness over existing circuit identification and feature attribution methods. Our work is a significant step toward better understanding the inner mechanisms of LLMs, which is crucial for improving them and ensuring their safety. Our code is available at https://github.com/JoakimEdin/gim.

Recent innovations in Transformer-based ranking models have advanced the state-of-the-art in information retrieval. However, these Transformers are computationally expensive, and their opaque hidden states make it hard to understand the ranking process. In this work, we modularize the Transformer ranker into separate modules for text representation and interaction. We show how this design enables substantially faster ranking using offline pre-computed representations and light-weight online interactions. The modular design is also easier to interpret and sheds light on the ranking process in Transformer rankers.

Prototype-based classification learning methods are known to be inherently interpretable. However, this paradigm suffers from major limitations compared to deep models, such as lower performance. This led to the development of the so-called deep Prototype-Based Networks (PBNs), also known as prototypical parts models. In this work, we analyze these models with respect to different properties, including interpretability. In particular, we focus on the Classification-by-Components (CBC) approach, which uses a probabilistic model to ensure interpretability and can be used as a shallow or deep architecture. We show that this model has several shortcomings, like creating contradicting explanations. Based on these findings, we propose an extension of CBC that solves these issues. Moreover, we prove that this extension has robustness guarantees and derive a loss that optimizes robustness. Additionally, our analysis shows that most (deep) PBNs are related to (deep) RBF classifiers, which implies that our robustness guarantees generalize to shallow RBF classifiers. The empirical evaluation demonstrates that our deep PBN yields state-of-the-art classification accuracy on different benchmarks while resolving the interpretability shortcomings of other approaches. Further, our shallow PBN variant outperforms other shallow PBNs while being inherently interpretable and exhibiting provable robustness guarantees.

Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across a wide range of NLP tasks, yet they remain prone to factual inaccuracies and hallucinations. This limitation poses significant risks in high-stakes domains such as healthcare, law, and scientific communication, where trust and verifiability are paramount. In this paper, we introduce DAVinCI - a Dual Attribution and Verification framework designed to enhance the factual reliability and interpretability of LLM outputs. DAVinCI operates in two stages: (i) it attributes generated claims to internal model components and external sources; (ii) it verifies each claim using entailment-based reasoning and confidence calibration. We evaluate DAVinCI across multiple datasets, including FEVER and CLIMATE-FEVER, and compare its performance against standard verification-only baselines. Our results show that DAVinCI significantly improves classification accuracy, attribution precision, recall, and F1-score by 5-20%. Through an extensive ablation study, we isolate the contributions of evidence span selection, recalibration thresholds, and retrieval quality. We also release a modular DAVinCI implementation that can be integrated into existing LLM pipelines. By bridging attribution and verification, DAVinCI offers a scalable path to auditable, trustworthy AI systems. This work contributes to the growing effort to make LLMs not only powerful but also accountable.

The increasing complexity of AI systems has made understanding their behavior a critical challenge. Numerous methods have been developed to attribute model behavior to three key aspects: input features, training data, and internal model components. However, these attribution methods are studied and applied rather independently, resulting in a fragmented landscape of approaches and terminology. This position paper argues that feature, data, and component attribution methods share fundamental similarities, and bridging them can benefit interpretability research. We conduct a detailed analysis of successful methods across three domains and present a unified view to demonstrate that these seemingly distinct methods employ similar approaches, such as perturbations, gradients, and linear approximations, differing primarily in their perspectives rather than core techniques. Our unified perspective enhances understanding of existing attribution methods, identifies shared concepts and challenges, makes this field more accessible to newcomers, and highlights new directions not only for attribution and interpretability but also for broader AI research, including model editing, steering, and regulation.

We present the LM Transparency Tool (LM-TT), an open-source interactive toolkit for analyzing the internal workings of Transformer-based language models. Differently from previously existing tools that focus on isolated parts of the decision-making process, our framework is designed to make the entire prediction process transparent, and allows tracing back model behavior from the top-layer representation to very fine-grained parts of the model. Specifically, it (1) shows the important part of the whole input-to-output information flow, (2) allows attributing any changes done by a model block to individual attention heads and feed-forward neurons, (3) allows interpreting the functions of those heads or neurons. A crucial part of this pipeline is showing the importance of specific model components at each step. As a result, we are able to look at the roles of model components only in cases where they are important for a prediction. Since knowing which components should be inspected is key for analyzing large models where the number of these components is extremely high, we believe our tool will greatly support the interpretability community both in research settings and in practical applications.

Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature importance scores, which identify features that are important for each individual input. However, how to systematically summarize and interpret such per sample feature importance scores itself is challenging. In this work, we propose principles and desiderata for concept based explanation, which goes beyond per-sample features to identify higher-level human-understandable concepts that apply across the entire dataset. We develop a new algorithm, ACE, to automatically extract visual concepts. Our systematic experiments demonstrate that \alg discovers concepts that are human-meaningful, coherent and important for the neural network's predictions.

Mechanistic interpretability aims to understand the behavior of neural networks by reverse-engineering their internal computations. However, current methods struggle to find clear interpretations of neural network activations because a decomposition of activations into computational features is missing. Individual neurons or model components do not cleanly correspond to distinct features or functions. We present a novel interpretability method that aims to overcome this limitation by transforming the activations of the network into a new basis - the Local Interaction Basis (LIB). LIB aims to identify computational features by removing irrelevant activations and interactions. Our method drops irrelevant activation directions and aligns the basis with the singular vectors of the Jacobian matrix between adjacent layers. It also scales features based on their importance for downstream computation, producing an interaction graph that shows all computationally-relevant features and interactions in a model. We evaluate the effectiveness of LIB on modular addition and CIFAR-10 models, finding that it identifies more computationally-relevant features that interact more sparsely, compared to principal component analysis. However, LIB does not yield substantial improvements in interpretability or interaction sparsity when applied to language models. We conclude that LIB is a promising theory-driven approach for analyzing neural networks, but in its current form is not applicable to large language models.

Part-prototype networks (e.g., ProtoPNet, ProtoTree and ProtoPool) have attracted broad research interest for their intrinsic interpretability and comparable accuracy to non-interpretable counterparts. However, recent works find that the interpretability from prototypes is fragile, due to the semantic gap between the similarities in the feature space and that in the input space. In this work, we strive to address this challenge by making the first attempt to quantitatively and objectively evaluate the interpretability of the part-prototype networks. Specifically, we propose two evaluation metrics, termed as consistency score and stability score, to evaluate the explanation consistency across images and the explanation robustness against perturbations, respectively, both of which are essential for explanations taken into practice. Furthermore, we propose an elaborated part-prototype network with a shallow-deep feature alignment (SDFA) module and a score aggregation (SA) module to improve the interpretability of prototypes. We conduct systematical evaluation experiments and provide substantial discussions to uncover the interpretability of existing part-prototype networks. Experiments on three benchmarks across nine architectures demonstrate that our model achieves significantly superior performance to the state of the art, in both the accuracy and interpretability. Codes are available at https://github.com/hqhQAQ/EvalProtoPNet.

Transformers exhibit impressive capabilities but are often regarded as black boxes due to challenges in understanding the complex nonlinear relationships between features. Interpreting machine learning models is of paramount importance to mitigate risks, and mechanistic interpretability is in particular of current interest as it opens up a window for guiding manual modifications and reverse-engineering solutions. In this work, we introduce contextual decomposition for transformers (CD-T), extending a prior work on CD for RNNs and CNNs, to address mechanistic interpretation computationally efficiently. CD-T is a flexible interpretation method for transformers. It can capture contributions of combinations of input features or source internal components (e.g. attention heads, feed-forward networks) to (1) final predictions or (2) the output of any target internal component. Using CD-T, we propose a novel algorithm for circuit discovery. On a real-world pathology report classification task: we show CD-T distills a more faithful circuit of attention heads with improved computational efficiency (speed up 2x) than a prior benchmark, path patching. As a versatile interpretation method, CD-T also exhibits exceptional capabilities for local interpretations. CD-T is shown to reliably find words and phrases of contrasting sentiment/topic on SST-2 and AGNews datasets. Through human experiments, we demonstrate CD-T enables users to identify the more accurate of two models and to better trust a model's outputs compared to alternative interpretation methods such as SHAP and LIME.

Explainable recommendation systems are important to enhance transparency, accuracy, and fairness. Beyond result-level explanations, model-level interpretations can provide valuable insights that allow developers to optimize system designs and implement targeted improvements. However, most current approaches depend on specialized model designs, which often lack generalization capabilities. Given the various kinds of recommendation models, existing methods have limited ability to effectively interpret them. To address this issue, we propose RecSAE, an automatic, generalizable probing method for interpreting the internal states of Recommendation models with Sparse AutoEncoder. RecSAE serves as a plug-in module that does not affect original models during interpretations, while also enabling predictable modifications to their behaviors based on interpretation results. Firstly, we train an autoencoder with sparsity constraints to reconstruct internal activations of recommendation models, making the RecSAE latents more interpretable and monosemantic than the original neuron activations. Secondly, we automated the construction of concept dictionaries based on the relationship between latent activations and input item sequences. Thirdly, RecSAE validates these interpretations by predicting latent activations on new item sequences using the concept dictionary and deriving interpretation confidence scores from precision and recall. We demonstrate RecSAE's effectiveness on two datasets, identifying hundreds of highly interpretable concepts from pure ID-based models. Latent ablation studies further confirm that manipulating latent concepts produces corresponding changes in model output behavior, underscoring RecSAE's utility for both understanding and targeted tuning recommendation models. Code and data are publicly available at https://github.com/Alice1998/RecSAE.

Concept-based interpretability methods offer a lens into the internals of foundation models by decomposing their embeddings into high-level concepts. These concept representations are most useful when they are compositional, meaning that the individual concepts compose to explain the full sample. We show that existing unsupervised concept extraction methods find concepts which are not compositional. To automatically discover compositional concept representations, we identify two salient properties of such representations, and propose Compositional Concept Extraction (CCE) for finding concepts which obey these properties. We evaluate CCE on five different datasets over image and text data. Our evaluation shows that CCE finds more compositional concept representations than baselines and yields better accuracy on four downstream classification tasks. Code and data are available at https://github.com/adaminsky/compositional_concepts .

Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet the task of interpretation appears underspecified. Papers provide diverse and sometimes non-overlapping motivations for interpretability, and offer myriad notions of what attributes render models interpretable. Despite this ambiguity, many papers proclaim interpretability axiomatically, absent further explanation. In this paper, we seek to refine the discourse on interpretability. First, we examine the motivations underlying interest in interpretability, finding them to be diverse and occasionally discordant. Then, we address model properties and techniques thought to confer interpretability, identifying transparency to humans and post-hoc explanations as competing notions. Throughout, we discuss the feasibility and desirability of different notions, and question the oft-made assertions that linear models are interpretable and that deep neural networks are not.

Understanding the decision-making processes of neural networks is a central goal of mechanistic interpretability. In the context of Large Language Models (LLMs), this involves uncovering the underlying mechanisms and identifying the roles of individual model components such as neurons and attention heads, as well as model abstractions such as the learned sparse features extracted by Sparse Autoencoders (SAEs). A rapidly growing line of work tackles this challenge by using powerful generator models to produce open-vocabulary, natural language concept descriptions for these components. In this paper, we provide the first survey of the emerging field of concept descriptions for model components and abstractions. We chart the key methods for generating these descriptions, the evolving landscape of automated and human metrics for evaluating them, and the datasets that underpin this research. Our synthesis reveals a growing demand for more rigorous, causal evaluation. By outlining the state of the art and identifying key challenges, this survey provides a roadmap for future research toward making models more transparent.

Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format. Nevertheless, they often preclude direct interpretation. While downstream tasks make use of these compressed representations, meaningful interpretation usually requires visualization using dimensionality reduction or specialized machine learning interpretability methods. This paper addresses the challenge of making such embeddings more interpretable and broadly useful, by employing Large Language Models (LLMs) to directly interact with embeddings -- transforming abstract vectors into understandable narratives. By injecting embeddings into LLMs, we enable querying and exploration of complex embedding data. We demonstrate our approach on a variety of diverse tasks, including: enhancing concept activation vectors (CAVs), communicating novel embedded entities, and decoding user preferences in recommender systems. Our work couples the immense information potential of embeddings with the interpretative power of LLMs.

Layer-wise normalization (LN) is an essential component of virtually all transformer-based large language models. While its effects on training stability are well documented, its role at inference time is poorly understood. Additionally, LN layers hinder mechanistic interpretability by introducing additional nonlinearities and increasing the interconnectedness of individual model components. Here, we show that all LN layers can be removed from every GPT-2 model with only a small increase in validation loss (e.g. +0.03 cross-entropy loss for GPT-2 XL). Thus, LN cannot play a substantial role in language modeling. We find that the amount of fine-tuning data needed for LN removal grows sublinearly with model parameters, suggesting scaling to larger models is feasible. We release a suite of LN-free GPT-2 models on Hugging Face. Furthermore, we test interpretability techniques on LN-free models. Direct logit attribution now gives the exact direct effect of individual components, while the accuracy of attribution patching does not significantly improve. We also confirm that GPT-2's "confidence neurons" are inactive in the LN-free models. Our work clarifies the role of LN layers in language modeling, showing that GPT-2-class models can function without LN layers. We hope that our LN-free analogs of the GPT-2 family of models will enable more precise interpretability research and improve our understanding of language models.

Interpretability and explainability have gained more and more attention in the field of machine learning as they are crucial when it comes to high-stakes decisions and troubleshooting. Since both provide information about predictors and their decision process, they are often seen as two independent means for one single end. This view has led to a dichotomous literature: explainability techniques designed for complex black-box models, or interpretable approaches ignoring the many explainability tools. In this position paper, we challenge the common idea that interpretability and explainability are substitutes for one another by listing their principal shortcomings and discussing how both of them mitigate the drawbacks of the other. In doing so, we call for a new perspective on interpretability and explainability, and works targeting both topics simultaneously, leveraging each of their respective assets.

Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Current feature description methods face two critical challenges: limited robustness and the flawed assumption that each neuron encodes only a single concept (monosemanticity), despite growing evidence that neurons are often polysemantic. This assumption restricts the expressiveness of feature descriptions and limits their ability to capture the full range of behaviors encoded in model internals. To address this, we introduce Polysemantic FeatuRe Identification and Scoring Method (PRISM), a novel framework that captures the inherent complexity of neural network features. Unlike prior approaches that assign a single description per feature, PRISM provides more nuanced descriptions for both polysemantic and monosemantic features. We apply PRISM to language models and, through extensive benchmarking against existing methods, demonstrate that our approach produces more accurate and faithful feature descriptions, improving both overall description quality (via a description score) and the ability to capture distinct concepts when polysemanticity is present (via a polysemanticity score).

Transformers are widely used to extract semantic meanings from input tokens, yet they usually operate as black-box models. In this paper, we present a simple yet informative decomposition of hidden states (or embeddings) of trained transformers into interpretable components. For any layer, embedding vectors of input sequence samples are represented by a tensor h in R^{C times T times d}. Given embedding vector h_{c,t} in R^d at sequence position t le T in a sequence (or context) c le C, extracting the mean effects yields the decomposition \[ h_{c,t} = \mu + pos_t + ctx_c + resid_{c,t} \] where mu is the global mean vector, pos_t and ctx_c are the mean vectors across contexts and across positions respectively, and resid_{c,t} is the residual vector. For popular transformer architectures and diverse text datasets, empirically we find pervasive mathematical structure: (1) (pos_t)_{t} forms a low-dimensional, continuous, and often spiral shape across layers, (2) (ctx_c)_c shows clear cluster structure that falls into context topics, and (3) (pos_t)_{t} and (ctx_c)_c are mutually nearly orthogonal. We argue that smoothness is pervasive and beneficial to transformers trained on languages, and our decomposition leads to improved model interpretability.

This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpretation and failure mode discovery. It equips a pre-trained vision-language model with a set of tools that support iterative experimentation on subcomponents of other models to explain their behavior. These include tools commonly used by human interpretability researchers: for synthesizing and editing inputs, computing maximally activating exemplars from real-world datasets, and summarizing and describing experimental results. Interpretability experiments proposed by MAIA compose these tools to describe and explain system behavior. We evaluate applications of MAIA to computer vision models. We first characterize MAIA's ability to describe (neuron-level) features in learned representations of images. Across several trained models and a novel dataset of synthetic vision neurons with paired ground-truth descriptions, MAIA produces descriptions comparable to those generated by expert human experimenters. We then show that MAIA can aid in two additional interpretability tasks: reducing sensitivity to spurious features, and automatically identifying inputs likely to be mis-classified.

A wide variety of model explanation approaches have been proposed in recent years, all guided by very different rationales and heuristics. In this paper, we take a new route and cast interpretability as a statistical inference problem. We propose a general deep probabilistic model designed to produce interpretable predictions. The model parameters can be learned via maximum likelihood, and the method can be adapted to any predictor network architecture and any type of prediction problem. Our method is a case of amortized interpretability models, where a neural network is used as a selector to allow for fast interpretation at inference time. Several popular interpretability methods are shown to be particular cases of regularised maximum likelihood for our general model. We propose new datasets with ground truth selection which allow for the evaluation of the features importance map. Using these datasets, we show experimentally that using multiple imputation provides more reasonable interpretations.

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons often encode multiple concepts has motivated a shift toward analyzing directions in activation space. A key question is how to find directions that capture interpretable features in an unsupervised manner. Current methods rely on dictionary learning with sparse autoencoders (SAEs), commonly trained over residual stream activations to learn directions from scratch. However, SAEs often struggle in causal evaluations and lack intrinsic interpretability, as their learning is not explicitly tied to the computations of the model. Here, we tackle these limitations by directly decomposing MLP activations with semi-nonnegative matrix factorization (SNMF), such that the learned features are (a) sparse linear combinations of co-activated neurons, and (b) mapped to their activating inputs, making them directly interpretable. Experiments on Llama 3.1, Gemma 2 and GPT-2 show that SNMF derived features outperform SAEs and a strong supervised baseline (difference-in-means) on causal steering, while aligning with human-interpretable concepts. Further analysis reveals that specific neuron combinations are reused across semantically-related features, exposing a hierarchical structure in the MLP's activation space. Together, these results position SNMF as a simple and effective tool for identifying interpretable features and dissecting concept representations in LLMs.

As vision-language models are deployed at scale, understanding their internal mechanisms becomes increasingly critical. Existing interpretability methods predominantly rely on activations, making them dataset-dependent, vulnerable to data bias, and often restricted to coarse head-level explanations. We introduce SITH (Semantic Inspection of Transformer Heads), a fully data-free, training-free framework that directly analyzes CLIP's vision transformer in weight space. For each attention head, we decompose its value-output matrix into singular vectors and interpret each one via COMP (Coherent Orthogonal Matching Pursuit), a new algorithm that explains them as sparse, semantically coherent combinations of human-interpretable concepts. We show that SITH yields coherent, faithful intra-head explanations, validated through reconstruction fidelity and interpretability experiments. This allows us to use SITH for precise, interpretable weight-space model edits that amplify or suppress specific concepts, improving downstream performance without retraining. Furthermore, we use SITH to study model adaptation, showing how fine-tuning primarily reweights a stable semantic basis rather than learning entirely new features.

Neural networks have achieved remarkable success across various fields. However, the lack of interpretability limits their practical use, particularly in critical decision-making scenarios. Post-hoc interpretability, which provides explanations for pre-trained models, is often at risk of robustness and fidelity. This has inspired a rising interest in self-interpretable neural networks, which inherently reveal the prediction rationale through the model structures. Although there exist surveys on post-hoc interpretability, a comprehensive and systematic survey of self-interpretable neural networks is still missing. To address this gap, we first collect and review existing works on self-interpretable neural networks and provide a structured summary of their methodologies from five key perspectives: attribution-based, function-based, concept-based, prototype-based, and rule-based self-interpretation. We also present concrete, visualized examples of model explanations and discuss their applicability across diverse scenarios, including image, text, graph data, and deep reinforcement learning. Additionally, we summarize existing evaluation metrics for self-interpretability and identify open challenges in this field, offering insights for future research. To support ongoing developments, we present a publicly accessible resource to track advancements in this domain: https://github.com/yangji721/Awesome-Self-Interpretable-Neural-Network.

Motivated by the hypothesis that neural network representations encode abstract, interpretable features as linearly accessible, approximately orthogonal directions, sparse autoencoders (SAEs) have become a popular tool in interpretability. However, recent work has demonstrated phenomenology of model representations that lies outside the scope of this hypothesis, showing signatures of hierarchical, nonlinear, and multi-dimensional features. This raises the question: do SAEs represent features that possess structure at odds with their motivating hypothesis? If not, does avoiding this mismatch help identify said features and gain further insights into neural network representations? To answer these questions, we take a construction-based approach and re-contextualize the popular matching pursuits (MP) algorithm from sparse coding to design MP-SAE -- an SAE that unrolls its encoder into a sequence of residual-guided steps, allowing it to capture hierarchical and nonlinearly accessible features. Comparing this architecture with existing SAEs on a mixture of synthetic and natural data settings, we show: (i) hierarchical concepts induce conditionally orthogonal features, which existing SAEs are unable to faithfully capture, and (ii) the nonlinear encoding step of MP-SAE recovers highly meaningful features, helping us unravel shared structure in the seemingly dichotomous representation spaces of different modalities in a vision-language model, hence demonstrating the assumption that useful features are solely linearly accessible is insufficient. We also show that the sequential encoder principle of MP-SAE affords an additional benefit of adaptive sparsity at inference time, which may be of independent interest. Overall, we argue our results provide credence to the idea that interpretability should begin with the phenomenology of representations, with methods emerging from assumptions that fit it.

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic interpretability -- which, in part, aims to identify model components (circuits) associated to specific interpretable mechanisms that make up a model capability -- can improve the precision and effectiveness of editing and unlearning. We find a stark difference in unlearning and edit robustness when training components localized by different methods. We highlight an important distinction between methods that localize components based primarily on preserving outputs, and those finding high level mechanisms with predictable intermediate states. In particular, localizing edits/unlearning to components associated with the lookup-table mechanism for factual recall 1) leads to more robust edits/unlearning across different input/output formats, and 2) resists attempts to relearn the unwanted information, while also reducing unintended side effects compared to baselines, on both a sports facts dataset and the CounterFact dataset across multiple models. We also find that certain localized edits disrupt the latent knowledge in the model more than any other baselines, making unlearning more robust to various attacks.

Mechanistic interpretability research faces a gap between analyzing simple circuits in toy tasks and discovering features in large models. To bridge this gap, we propose text-to-SQL generation as an ideal task to study, as it combines the formal structure of toy tasks with real-world complexity. We introduce TinySQL, a synthetic dataset, progressing from basic to advanced SQL operations, and train models ranging from 33M to 1B parameters to establish a comprehensive testbed for interpretability. We apply multiple complementary interpretability techniques, including Edge Attribution Patching and Sparse Autoencoders, to identify minimal circuits and components supporting SQL generation. We compare circuits for different SQL subskills, evaluating their minimality, reliability, and identifiability. Finally, we conduct a layerwise logit lens analysis to reveal how models compose SQL queries across layers: from intent recognition to schema resolution to structured generation. Our work provides a robust framework for probing and comparing interpretability methods in a structured, progressively complex setting.

Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods, such as direct logit attribution (DLA) and sparse autoencoders (SAEs), provide restricted insight due to limitations such as the model's output vocabulary or unclear feature names. This work introduces Hyperdimensional Probe, a novel paradigm for decoding information from the LLM vector space. It combines ideas from symbolic representations and neural probing to project the model's residual stream into interpretable concepts via Vector Symbolic Architectures (VSAs). This probe combines the strengths of SAEs and conventional probes while overcoming their key limitations. We validate our decoding paradigm with controlled input-completion tasks, probing the model's final state before next-token prediction on inputs spanning syntactic pattern recognition, key-value associations, and abstract inference. We further assess it in a question-answering setting, examining the state of the model both before and after text generation. Our experiments show that our probe reliably extracts meaningful concepts across varied LLMs, embedding sizes, and input domains, also helping identify LLM failures. Our work advances information decoding in LLM vector space, enabling extracting more informative, interpretable, and structured features from neural representations.

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that correspond to human-interpretable features. In this paper, we investigate the effectiveness of SAE-based explainability approaches for sentence classification, a domain where such methods have not been extensively explored. We present a novel SAE-based model ClassifSAE tailored for text classification, leveraging a specialized classifier head and incorporating an activation rate sparsity loss. We benchmark this architecture against established methods such as ConceptShap, Independent Component Analysis, HI-Concept and a standard TopK-SAE baseline. Our evaluation covers several classification benchmarks and backbone LLMs. We further enrich our analysis with two novel metrics for measuring the precision of concept-based explanations, using an external sentence encoder. Our empirical results show that ClassifSAE improves both the causality and interpretability of the extracted features.

Graph Transformers (GTs) have emerged as powerful architectures for graph-structured data, yet remain constrained by rigid designs and lack quantifiable interpretability. Current state-of-the-art GTs commit to fixed GNN types across all layers, missing potential benefits of depth-specific component selection, while their complex architectures become opaque where performance gains cannot be distinguished between meaningful patterns and spurious correlations. We redesign GT attention through asymmetry, decoupling structural encoding from feature representation: queries derive from node features while keys and values come from GNN transformations. Within this framework, we use Differentiable ARchiTecture Search (DARTS) to select optimal GNN operators at each layer, enabling depth-wise heterogeneity inside transformer attention itself (DARTS-GT). To understand discovered architectures, we develop the first quantitative interpretability framework for GTs through causal ablation. Our metrics (Head-deviation, Specialization, and Focus), identify which heads and nodes drive predictions while enabling model comparison. Experiments across eight benchmarks show DARTS-GT achieves state-of-the-art on four datasets while remaining competitive on others, with discovered architectures revealing dataset-specific patterns. Our interpretability analysis reveals that visual attention salience and causal importance do not always correlate, indicating widely used visualization approaches may miss components that actually matter. Crucially, heterogeneous architectures found by DARTS-GT consistently produced more interpretable models than baselines, establishing that Graph Transformers need not choose between performance and interpretability.

Gradient-based methods for instance-based explanation for large language models (LLMs) are hindered by the immense dimensionality of model gradients. In practice, influence estimation is restricted to a subset of model parameters to make computation tractable, but this subset is often chosen ad hoc and rarely justified by systematic evaluation. This paper investigates if it is better to create low-dimensional representations by selecting a small, architecturally informed subset of model components or by projecting the full gradients into a lower-dimensional space. Using a novel benchmark, we show that a greedily selected subset of components captures the information about training data influence needed for a retrieval task more effectively than either the full gradient or random projection. We further find that this approach is more computationally efficient than random projection, demonstrating that targeted component selection is a practical strategy for making instance-based explanations of large models more computationally feasible.

Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this crucial topic. We also identify 10 technical challenge areas in interpretable machine learning and provide history and background on each problem. Some of these problems are classically important, and some are recent problems that have arisen in the last few years. These problems are: (1) Optimizing sparse logical models such as decision trees; (2) Optimization of scoring systems; (3) Placing constraints into generalized additive models to encourage sparsity and better interpretability; (4) Modern case-based reasoning, including neural networks and matching for causal inference; (5) Complete supervised disentanglement of neural networks; (6) Complete or even partial unsupervised disentanglement of neural networks; (7) Dimensionality reduction for data visualization; (8) Machine learning models that can incorporate physics and other generative or causal constraints; (9) Characterization of the "Rashomon set" of good models; and (10) Interpretable reinforcement learning. This survey is suitable as a starting point for statisticians and computer scientists interested in working in interpretable machine learning.

Approaching new data can be quite deterrent; you do not know how your categories of interest are realized in it, commonly, there is no labeled data at hand, and the performance of domain adaptation methods is unsatisfactory. Aiming to assist domain experts in their first steps into a new task over a new corpus, we present an unsupervised approach to reveal complex rules which cluster the unexplored corpus by its prominent categories (or facets). These rules are human-readable, thus providing an important ingredient which has become in short supply lately - explainability. Each rule provides an explanation for the commonality of all the texts it clusters together. We present an extensive evaluation of the usefulness of these rules in identifying target categories, as well as a user study which assesses their interpretability.

We argue that robustness of explanations---i.e., that similar inputs should give rise to similar explanations---is a key desideratum for interpretability. We introduce metrics to quantify robustness and demonstrate that current methods do not perform well according to these metrics. Finally, we propose ways that robustness can be enforced on existing interpretability approaches.

We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model behaviors. Circuits identified in prior work consist of polysemantic and difficult-to-interpret units like attention heads or neurons, rendering them unsuitable for many downstream applications. In contrast, sparse feature circuits enable detailed understanding of unanticipated mechanisms. Because they are based on fine-grained units, sparse feature circuits are useful for downstream tasks: We introduce SHIFT, where we improve the generalization of a classifier by ablating features that a human judges to be task-irrelevant. Finally, we demonstrate an entirely unsupervised and scalable interpretability pipeline by discovering thousands of sparse feature circuits for automatically discovered model behaviors.

Interpreting the internal activations of neural networks can produce more faithful explanations of their behavior, but is difficult due to the complex structure of activation space. Existing approaches to scalable interpretability use hand-designed agents that make and test hypotheses about how internal activations relate to external behavior. We propose to instead turn this task into an end-to-end training objective, by training interpretability assistants to accurately predict model behavior from activations through a communication bottleneck. Specifically, an encoder compresses activations to a sparse list of concepts, and a decoder reads this list and answers a natural language question about the model. We show how to pretrain this assistant on large unstructured data, then finetune it to answer questions. The resulting architecture, which we call a Predictive Concept Decoder, enjoys favorable scaling properties: the auto-interp score of the bottleneck concepts improves with data, as does the performance on downstream applications. Specifically, PCDs can detect jailbreaks, secret hints, and implanted latent concepts, and are able to accurately surface latent user attributes.

As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpretability, there is very little consensus on what interpretable machine learning is and how it should be measured. In this position paper, we first define interpretability and describe when interpretability is needed (and when it is not). Next, we suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.

Interpretability methods seek to understand language model representations, yet the outputs of most such methods -- circuits, vectors, scalars -- are not immediately human-interpretable. In response, we introduce LatentQA, the task of answering open-ended questions about model activations in natural language. Towards solving LatentQA, we propose Latent Interpretation Tuning (LIT), which finetunes a decoder LLM on a dataset of activations and associated question-answer pairs, similar to how visual instruction tuning trains on question-answer pairs associated with images. We use the decoder for diverse reading applications, such as extracting relational knowledge from representations or uncovering system prompts governing model behavior. Our decoder also specifies a differentiable loss that we use to control models, such as debiasing models on stereotyped sentences and controlling the sentiment of generations. Finally, we extend LatentQA to reveal harmful model capabilities, such as generating recipes for bioweapons and code for hacking.

Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them human interpretable and enables us to assign semantics to what was seen only as numerical vectors. In this paper, we interpret LM attention heads and memory values, the vectors the models dynamically create and recall while processing a given input. By analyzing the tokens they represent through this projection, we identify patterns in the information flow inside the attention mechanism. Based on these discoveries, we create a tool to visualize a forward pass of Generative Pre-trained Transformers (GPTs) as an interactive flow graph, with nodes representing neurons or hidden states and edges representing the interactions between them. Our visualization simplifies huge amounts of data into easy-to-read plots that reflect why models output their results. We demonstrate the utility of our modeling by identifying the effect LM components have on the intermediate processing in the model before outputting a prediction. For instance, we discover that layer norms are used as semantic filters and find neurons that act as regularization vectors.

Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable circuits by constraining most of their weights to be zeros, so that each neuron only has a few connections. To recover fine-grained circuits underlying each of several hand-crafted tasks, we prune the models to isolate the part responsible for the task. These circuits often contain neurons and residual channels that correspond to natural concepts, with a small number of straightforwardly interpretable connections between them. We study how these models scale and find that making weights sparser trades off capability for interpretability, and scaling model size improves the capability-interpretability frontier. However, scaling sparse models beyond tens of millions of nonzero parameters while preserving interpretability remains a challenge. In addition to training weight-sparse models de novo, we show preliminary results suggesting our method can also be adapted to explain existing dense models. Our work produces circuits that achieve an unprecedented level of human understandability and validates them with considerable rigor.

Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning systems. It is also related to many ethical problems, e.g., algorithmic discrimination. Moreover, interpretability is a desired property for deep networks to become powerful tools in other research fields, e.g., drug discovery and genomics. In this survey, we conduct a comprehensive review of the neural network interpretability research. We first clarify the definition of interpretability as it has been used in many different contexts. Then we elaborate on the importance of interpretability and propose a novel taxonomy organized along three dimensions: type of engagement (passive vs. active interpretation approaches), the type of explanation, and the focus (from local to global interpretability). This taxonomy provides a meaningful 3D view of distribution of papers from the relevant literature as two of the dimensions are not simply categorical but allow ordinal subcategories. Finally, we summarize the existing interpretability evaluation methods and suggest possible research directions inspired by our new taxonomy.

Interpretability research often aims to predict how a model will respond to targeted interventions on specific mechanisms. However, it rarely predicts how a model will respond to unseen input data. This paper explores the promises and challenges of interpretability as a tool for predicting out-of-distribution (OOD) model behavior. Specifically, we investigate the correspondence between attention patterns and OOD generalization in hundreds of Transformer models independently trained on a synthetic classification task. These models exhibit several distinct systematic generalization rules OOD, forming a diverse population for correlational analysis. In this setting, we find that simple observational tools from interpretability can predict OOD performance. In particular, when in-distribution attention exhibits hierarchical patterns, the model is likely to generalize hierarchically on OOD data -- even when the rule's implementation does not rely on these hierarchical patterns, according to ablation tests. Our findings offer a proof-of-concept to motivate further interpretability work on predicting unseen model behavior.

The rapid development of Artificial Intelligence (AI) has revolutionized numerous fields, with large language models (LLMs) and computer vision (CV) systems driving advancements in natural language understanding and visual processing, respectively. The convergence of these technologies has catalyzed the rise of multimodal AI, enabling richer, cross-modal understanding that spans text, vision, audio, and video modalities. Multimodal large language models (MLLMs), in particular, have emerged as a powerful framework, demonstrating impressive capabilities in tasks like image-text generation, visual question answering, and cross-modal retrieval. Despite these advancements, the complexity and scale of MLLMs introduce significant challenges in interpretability and explainability, essential for establishing transparency, trustworthiness, and reliability in high-stakes applications. This paper provides a comprehensive survey on the interpretability and explainability of MLLMs, proposing a novel framework that categorizes existing research across three perspectives: (I) Data, (II) Model, (III) Training \& Inference. We systematically analyze interpretability from token-level to embedding-level representations, assess approaches related to both architecture analysis and design, and explore training and inference strategies that enhance transparency. By comparing various methodologies, we identify their strengths and limitations and propose future research directions to address unresolved challenges in multimodal explainability. This survey offers a foundational resource for advancing interpretability and transparency in MLLMs, guiding researchers and practitioners toward developing more accountable and robust multimodal AI systems.

In many scenarios, the interpretability of machine learning models is a highly required but difficult task. To explain the individual predictions of such models, local model-agnostic approaches have been proposed. However, the process generating the explanations can be, for a user, as mysterious as the prediction to be explained. Furthermore, interpretability methods frequently lack theoretical guarantees, and their behavior on simple models is frequently unknown. While it is difficult, if not impossible, to ensure that an explainer behaves as expected on a cutting-edge model, we can at least ensure that everything works on simple, already interpretable models. In this paper, we present a theoretical analysis of Anchors (Ribeiro et al., 2018): a popular rule-based interpretability method that highlights a small set of words to explain a text classifier's decision. After formalizing its algorithm and providing useful insights, we demonstrate mathematically that Anchors produces meaningful results when used with linear text classifiers on top of a TF-IDF vectorization. We believe that our analysis framework can aid in the development of new explainability methods based on solid theoretical foundations.

Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed. First, researchers choose a metric and dataset that elicit the desired model behavior. Then, they apply activation patching to find which abstract neural network units are involved in the behavior. By varying the dataset, metric, and units under investigation, researchers can understand the functionality of each component. We automate one of the process' steps: to identify the circuit that implements the specified behavior in the model's computational graph. We propose several algorithms and reproduce previous interpretability results to validate them. For example, the ACDC algorithm rediscovered 5/5 of the component types in a circuit in GPT-2 Small that computes the Greater-Than operation. ACDC selected 68 of the 32,000 edges in GPT-2 Small, all of which were manually found by previous work. Our code is available at https://github.com/ArthurConmy/Automatic-Circuit-Discovery.

Concept-based interpretability methods aim to explain deep neural network model predictions using a predefined set of semantic concepts. These methods evaluate a trained model on a new, "probe" dataset and correlate model predictions with the visual concepts labeled in that dataset. Despite their popularity, they suffer from limitations that are not well-understood and articulated by the literature. In this work, we analyze three commonly overlooked factors in concept-based explanations. First, the choice of the probe dataset has a profound impact on the generated explanations. Our analysis reveals that different probe datasets may lead to very different explanations, and suggests that the explanations are not generalizable outside the probe dataset. Second, we find that concepts in the probe dataset are often less salient and harder to learn than the classes they claim to explain, calling into question the correctness of the explanations. We argue that only visually salient concepts should be used in concept-based explanations. Finally, while existing methods use hundreds or even thousands of concepts, our human studies reveal a much stricter upper bound of 32 concepts or less, beyond which the explanations are much less practically useful. We make suggestions for future development and analysis of concept-based interpretability methods. Code for our analysis and user interface can be found at https://github.com/princetonvisualai/OverlookedFactors

Neurons in large language models often exhibit polysemanticity, simultaneously encoding multiple unrelated concepts and obscuring interpretability. Instead of relying on post-hoc methods, we present MoE-X, a Mixture-of-Experts (MoE) language model designed to be intrinsically interpretable. Our approach is motivated by the observation that, in language models, wider networks with sparse activations are more likely to capture interpretable factors. However, directly training such large sparse networks is computationally prohibitive. MoE architectures offer a scalable alternative by activating only a subset of experts for any given input, inherently aligning with interpretability objectives. In MoE-X, we establish this connection by rewriting the MoE layer as an equivalent sparse, large MLP. This approach enables efficient scaling of the hidden size while maintaining sparsity. To further enhance interpretability, we enforce sparse activation within each expert and redesign the routing mechanism to prioritize experts with the highest activation sparsity. These designs ensure that only the most salient features are routed and processed by the experts. We evaluate MoE-X on chess and natural language tasks, showing that it achieves performance comparable to dense models while significantly improving interpretability. MoE-X achieves a perplexity better than GPT-2, with interpretability surpassing even sparse autoencoder (SAE)-based approaches.

We introduce a new approach to systematically map features discovered by sparse autoencoder across consecutive layers of large language models, extending earlier work that examined inter-layer feature links. By using a data-free cosine similarity technique, we trace how specific features persist, transform, or first appear at each stage. This method yields granular flow graphs of feature evolution, enabling fine-grained interpretability and mechanistic insights into model computations. Crucially, we demonstrate how these cross-layer feature maps facilitate direct steering of model behavior by amplifying or suppressing chosen features, achieving targeted thematic control in text generation. Together, our findings highlight the utility of a causal, cross-layer interpretability framework that not only clarifies how features develop through forward passes but also provides new means for transparent manipulation of large language models.

Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc evaluations and do not share theoretical foundations, making it difficult to measure progress and compare the pros and cons of different techniques. Furthermore, while mechanistic understanding is frequently discussed, the basic causal units underlying these mechanisms are often not explicitly defined. In this paper, we propose a perspective on interpretability research grounded in causal mediation analysis. Specifically, we describe the history and current state of interpretability taxonomized according to the types of causal units (mediators) employed, as well as methods used to search over mediators. We discuss the pros and cons of each mediator, providing insights as to when particular kinds of mediators and search methods are most appropriate depending on the goals of a given study. We argue that this framing yields a more cohesive narrative of the field, as well as actionable insights for future work. Specifically, we recommend a focus on discovering new mediators with better trade-offs between human-interpretability and compute-efficiency, and which can uncover more sophisticated abstractions from neural networks than the primarily linear mediators employed in current work. We also argue for more standardized evaluations that enable principled comparisons across mediator types, such that we can better understand when particular causal units are better suited to particular use cases.

Recent work by Anthropic on Mechanistic interpretability claims to understand and control Large Language Models by extracting human-interpretable features from their neural activation patterns using sparse autoencoders (SAEs). If successful, this approach offers one of the most promising routes for human oversight in AI safety. We conduct an initial stress-test of these claims by replicating their main results with open-source SAEs for Llama 3.1. While we successfully reproduce basic feature extraction and steering capabilities, our investigation suggests that major caution is warranted regarding the generalizability of these claims. We find that feature steering exhibits substantial fragility, with sensitivity to layer selection, steering magnitude, and context. We observe non-standard activation behavior and demonstrate the difficulty to distinguish thematically similar features from one another. While SAE-based interpretability produces compelling demonstrations in selected cases, current methods often fall short of the systematic reliability required for safety-critical applications. This suggests a necessary shift in focus from prioritizing interpretability of internal representations toward reliable prediction and control of model output. Our work contributes to a more nuanced understanding of what mechanistic interpretability has achieved and highlights fundamental challenges for AI safety that remain unresolved.

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a means to understand the inner workings of LLMs. Among various mechanistic interpretability approaches, Sparse Autoencoders (SAEs) have emerged as a promising method due to their ability to disentangle the complex, superimposed features within LLMs into more interpretable components. This paper presents a comprehensive survey of SAEs for interpreting and understanding the internal workings of LLMs. Our major contributions include: (1) exploring the technical framework of SAEs, covering basic architecture, design improvements, and effective training strategies; (2) examining different approaches to explaining SAE features, categorized into input-based and output-based explanation methods; (3) discussing evaluation methods for assessing SAE performance, covering both structural and functional metrics; and (4) investigating real-world applications of SAEs in understanding and manipulating LLM behaviors.

Recent works have extended notions of feature importance to semantic concepts that are inherently interpretable to the users interacting with a black-box predictive model. Yet, precise statistical guarantees, such as false positive rate control, are needed to communicate findings transparently and to avoid unintended consequences in real-world scenarios. In this paper, we formalize the global (i.e., over a population) and local (i.e., for a sample) statistical importance of semantic concepts for the predictions of opaque models, by means of conditional independence, which allows for rigorous testing. We use recent ideas of sequential kernelized testing (SKIT) to induce a rank of importance across concepts, and showcase the effectiveness and flexibility of our framework on synthetic datasets as well as on image classification tasks using vision-language models such as CLIP.

The visual representation of a pre-trained model prioritizes the classifiability on downstream tasks, while the widespread applications for pre-trained visual models have posed new requirements for representation interpretability. However, it remains unclear whether the pre-trained representations can achieve high interpretability and classifiability simultaneously. To answer this question, we quantify the representation interpretability by leveraging its correlation with the ratio of interpretable semantics within the representations. Given the pre-trained representations, only the interpretable semantics can be captured by interpretations, whereas the uninterpretable part leads to information loss. Based on this fact, we propose the Inherent Interpretability Score (IIS) that evaluates the information loss, measures the ratio of interpretable semantics, and quantifies the representation interpretability. In the evaluation of the representation interpretability with different classifiability, we surprisingly discover that the interpretability and classifiability are positively correlated, i.e., representations with higher classifiability provide more interpretable semantics that can be captured in the interpretations. This observation further supports two benefits to the pre-trained representations. First, the classifiability of representations can be further improved by fine-tuning with interpretability maximization. Second, with the classifiability improvement for the representations, we obtain predictions based on their interpretations with less accuracy degradation. The discovered positive correlation and corresponding applications show that practitioners can unify the improvements in interpretability and classifiability for pre-trained vision models. Codes are available at https://github.com/ssfgunner/IIS.

An approach to improve neural network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We define a measure for clusterability and show that pre-trained models form highly enmeshed clusters via spectral graph clustering. We thus train models to be more modular using a "clusterability loss" function that encourages the formation of non-interacting clusters. Using automated interpretability techniques, we show that our method can help train models that are more modular and learn different, disjoint, and smaller circuits. We investigate CNNs trained on MNIST and CIFAR, small transformers trained on modular addition, and language models. Our approach provides a promising direction for training neural networks that learn simpler functions and are easier to interpret.

Despite a sea of interpretability methods that can produce plausible explanations, the field has also empirically seen many failure cases of such methods. In light of these results, it remains unclear for practitioners how to use these methods and choose between them in a principled way. In this paper, we show that for moderately rich model classes (easily satisfied by neural networks), any feature attribution method that is complete and linear -- for example, Integrated Gradients and SHAP -- can provably fail to improve on random guessing for inferring model behaviour. Our results apply to common end-tasks such as characterizing local model behaviour, identifying spurious features, and algorithmic recourse. One takeaway from our work is the importance of concretely defining end-tasks: once such an end-task is defined, a simple and direct approach of repeated model evaluations can outperform many other complex feature attribution methods.

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse, interpretable features, and have been applied to MLP layers and the residual stream. In this work we train SAEs on attention layer outputs and show that also here SAEs find a sparse, interpretable decomposition. We demonstrate this on transformers from several model families and up to 2B parameters. We perform a qualitative study of the features computed by attention layers, and find multiple families: long-range context, short-range context and induction features. We qualitatively study the role of every head in GPT-2 Small, and estimate that at least 90% of the heads are polysemantic, i.e. have multiple unrelated roles. Further, we show that Sparse Autoencoders are a useful tool that enable researchers to explain model behavior in greater detail than prior work. For example, we explore the mystery of why models have so many seemingly redundant induction heads, use SAEs to motivate the hypothesis that some are long-prefix whereas others are short-prefix, and confirm this with more rigorous analysis. We use our SAEs to analyze the computation performed by the Indirect Object Identification circuit (Wang et al.), validating that the SAEs find causally meaningful intermediate variables, and deepening our understanding of the semantics of the circuit. We open-source the trained SAEs and a tool for exploring arbitrary prompts through the lens of Attention Output SAEs.

The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, a silent, recurrent and acknowledged issue in this area is the lack of consensus regarding its terminology. In particular, each new contribution seems to rely on its own (and often intuitive) version of terms like "explanation" and "interpretation". Such disarray encumbers the consolidation of advances in the field towards the fulfillment of scientific and regulatory demands e.g., when comparing methods or establishing their compliance with respect to biases and fairness constraints. We propose a theoretical framework that not only provides concrete definitions for these terms, but it also outlines all steps necessary to produce explanations and interpretations. The framework also allows for existing contributions to be re-contextualized such that their scope can be measured, thus making them comparable to other methods. We show that this framework is compliant with desiderata on explanations, on interpretability and on evaluation metrics. We present a use-case showing how the framework can be used to compare LIME, SHAP and MDNet, establishing their advantages and shortcomings. Finally, we discuss relevant trends in XAI as well as recommendations for future work, all from the standpoint of our framework.

Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for interpreting transformer-based language models (LMs), resulting in many novel insights yet introducing new challenges. However, there has not been work that comprehensively reviews these insights and challenges, particularly as a guide for newcomers to this field. To fill this gap, we provide a comprehensive survey from a task-centric perspective, organizing the taxonomy of MI research around specific research questions or tasks. We outline the fundamental objects of study in MI, along with the techniques, evaluation methods, and key findings for each task in the taxonomy. In particular, we present a task-centric taxonomy as a roadmap for beginners to navigate the field by helping them quickly identify impactful problems in which they are most interested and leverage MI for their benefit. Finally, we discuss the current gaps in the field and suggest potential future directions for MI research.

With the recent addition of Retrieval-Augmented Generation (RAG), the scope and importance of Information Retrieval (IR) has expanded. As a result, the importance of a deeper understanding of IR models also increases. However, interpretability in IR remains under-explored, especially when it comes to the models' inner mechanisms. In this paper, we explore the possibility of adapting Integrated Gradient-based methods in an IR context to identify the role of individual neurons within the model. In particular, we provide new insights into the role of what we call "relevance" neurons, as well as how they deal with unseen data. Finally, we carry out an in-depth pruning study to validate our findings.

Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their effectiveness in disentangling semantic concepts. By training SAEs on embeddings of over 420,000 scientific paper abstracts from computer science and astronomy, we show that the resulting sparse representations maintain semantic fidelity while offering interpretability. We analyse these learned features, exploring their behaviour across different model capacities and introducing a novel method for identifying ``feature families'' that represent related concepts at varying levels of abstraction. To demonstrate the practical utility of our approach, we show how these interpretable features can be used to precisely steer semantic search, allowing for fine-grained control over query semantics. This work bridges the gap between the semantic richness of dense embeddings and the interpretability of sparse representations. We open source our embeddings, trained sparse autoencoders, and interpreted features, as well as a web app for exploring them.

In large language models (LLMs), each block operates on the residual stream to map input token sequences to output token distributions. However, most of the interpretability literature focuses on internal latent representations, leaving token-space dynamics underexplored. The high dimensionality and categoricity of token distributions hinder their analysis, as standard statistical descriptors are not suitable. We show that the entropy of logit-lens predictions overcomes these issues. In doing so, it provides a per-layer scalar, permutation-invariant metric. We introduce Entropy-Lens to distill the token-space dynamics of the residual stream into a low-dimensional signal. We call this signal the entropy profile. We apply our method to a variety of model sizes and families, showing that (i) entropy profiles uncover token prediction dynamics driven by expansion and pruning strategies; (ii) these dynamics are family-specific and invariant under depth rescaling; (iii) they are characteristic of task type and output format; (iv) these strategies have unequal impact on downstream performance, with the expansion strategy usually being more critical. Ultimately, our findings further enhance our understanding of the residual stream, enabling a granular assessment of how information is processed across model depth.

Interpretability is a key challenge in fostering trust for Large Language Models (LLMs), which stems from the complexity of extracting reasoning from model's parameters. We present the Frame Representation Hypothesis, a theoretically robust framework grounded in the Linear Representation Hypothesis (LRH) to interpret and control LLMs by modeling multi-token words. Prior research explored LRH to connect LLM representations with linguistic concepts, but was limited to single token analysis. As most words are composed of several tokens, we extend LRH to multi-token words, thereby enabling usage on any textual data with thousands of concepts. To this end, we propose words can be interpreted as frames, ordered sequences of vectors that better capture token-word relationships. Then, concepts can be represented as the average of word frames sharing a common concept. We showcase these tools through Top-k Concept-Guided Decoding, which can intuitively steer text generation using concepts of choice. We verify said ideas on Llama 3.1, Gemma 2, and Phi 3 families, demonstrating gender and language biases, exposing harmful content, but also potential to remediate them, leading to safer and more transparent LLMs. Code is available at https://github.com/phvv-me/frame-representation-hypothesis.git

Understanding Transformer-based models has attracted significant attention, as they lie at the heart of recent technological advances across machine learning. While most interpretability methods rely on running models over inputs, recent work has shown that a zero-pass approach, where parameters are interpreted directly without a forward/backward pass is feasible for some Transformer parameters, and for two-layer attention networks. In this work, we present a theoretical analysis where all parameters of a trained Transformer are interpreted by projecting them into the embedding space, that is, the space of vocabulary items they operate on. We derive a simple theoretical framework to support our arguments and provide ample evidence for its validity. First, an empirical analysis showing that parameters of both pretrained and fine-tuned models can be interpreted in embedding space. Second, we present two applications of our framework: (a) aligning the parameters of different models that share a vocabulary, and (b) constructing a classifier without training by ``translating'' the parameters of a fine-tuned classifier to parameters of a different model that was only pretrained. Overall, our findings open the door to interpretation methods that, at least in part, abstract away from model specifics and operate in the embedding space only.

Despite strong performance in audio perception tasks, large audio-language models (AudioLLMs) remain opaque to interpretation. A major factor behind this lack of interpretability is that individual neurons in these models frequently activate in response to several unrelated concepts. We introduce the first mechanistic interpretability framework for AudioLLMs, leveraging sparse autoencoders (SAEs) to disentangle polysemantic activations into monosemantic features. Our pipeline identifies representative audio clips, assigns meaningful names via automated captioning, and validates concepts through human evaluation and steering. Experiments show that AudioLLMs encode structured and interpretable features, enhancing transparency and control. This work provides a foundation for trustworthy deployment in high-stakes domains and enables future extensions to larger models, multilingual audio, and more fine-grained paralinguistic features. Project URL: https://townim-faisal.github.io/AutoInterpret-AudioLLM/

In this work, we study the challenge of providing human-understandable descriptions for failure modes in trained image classification models. Existing works address this problem by first identifying clusters (or directions) of incorrectly classified samples in a latent space and then aiming to provide human-understandable text descriptions for them. We observe that in some cases, describing text does not match well with identified failure modes, partially owing to the fact that shared interpretable attributes of failure modes may not be captured using clustering in the feature space. To improve on these shortcomings, we propose a novel approach that prioritizes interpretability in this problem: we start by obtaining human-understandable concepts (tags) of images in the dataset and then analyze the model's behavior based on the presence or absence of combinations of these tags. Our method also ensures that the tags describing a failure mode form a minimal set, avoiding redundant and noisy descriptions. Through several experiments on different datasets, we show that our method successfully identifies failure modes and generates high-quality text descriptions associated with them. These results highlight the importance of prioritizing interpretability in understanding model failures.

Large neural models are increasingly deployed in high-stakes settings, raising concerns about whether their behavior reliably aligns with human values. Interpretability provides a route to internal transparency by revealing the computations that drive outputs. We argue that interpretability especially mechanistic approaches should be treated as a design principle for alignment, not an auxiliary diagnostic tool. Post-hoc methods such as LIME or SHAP offer intuitive but correlational explanations, while mechanistic techniques like circuit tracing or activation patching yield causal insight into internal failures, including deceptive or misaligned reasoning that behavioral methods like RLHF, red teaming, or Constitutional AI may overlook. Despite these advantages, interpretability faces challenges of scalability, epistemic uncertainty, and mismatches between learned representations and human concepts. Our position is that progress on safe and trustworthy AI will depend on making interpretability a first-class objective of AI research and development, ensuring that systems are not only effective but also auditable, transparent, and aligned with human intent.

Recent advancements in machine learning have spurred growing interests in automated interpreting quality assessment. Nevertheless, existing research suffers from insufficient examination of language use quality, unsatisfactory modeling effectiveness due to data scarcity and imbalance, and a lack of efforts to explain model predictions. To address these gaps, we propose a multi-dimensional modeling framework that integrates feature engineering, data augmentation, and explainable machine learning. This approach prioritizes explainability over ``black box'' predictions by utilizing only construct-relevant, transparent features and conducting Shapley Value (SHAP) analysis. Our results demonstrate strong predictive performance on a novel English-Chinese consecutive interpreting dataset, identifying BLEURT and CometKiwi scores to be the strongest predictive features for fidelity, pause-related features for fluency, and Chinese-specific phraseological diversity metrics for language use. Overall, by placing particular emphasis on explainability, we present a scalable, reliable, and transparent alternative to traditional human evaluation, facilitating the provision of detailed diagnostic feedback for learners and supporting self-regulated learning advantages not afforded by automated scores in isolation.

Network interpretation as an effort to reveal the features learned by a network remains largely visualization-based. In this paper, our goal is to tackle semantic network interpretation at both filter and decision level. For filter-level interpretation, we represent the concepts a filter encodes with a probability distribution of visual attributes. The decision-level interpretation is achieved by textual summarization that generates an explanatory sentence containing clues behind a network's decision. A Bayesian inference algorithm is proposed to automatically associate filters and network decisions with visual attributes. Human study confirms that the semantic interpretation is a beneficial alternative or complement to visualization methods. We demonstrate the crucial role that semantic network interpretation can play in understanding a network's failure patterns. More importantly, semantic network interpretation enables a better understanding of the correlation between a model's performance and its distribution metrics like filter selectivity and concept sparseness.

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level analysis and natural language explanations by (i) identifying causally important attention heads via activation patching, (ii) generating explanations using both template-based and LLM-based methods, and (iii) evaluating faithfulness using ERASER-style metrics adapted for circuit-level attribution. We evaluate on the Indirect Object Identification (IOI) task in GPT-2 Small (124M parameters), identifying six attention heads accounting for 61.4% of the logit difference. Our circuit-based explanations achieve 100% sufficiency but only 22% comprehensiveness, revealing distributed backup mechanisms. LLM-generated explanations outperform template baselines by 64% on quality metrics. We find no correlation (r = 0.009) between model confidence and explanation faithfulness, and identify three failure categories explaining when explanations diverge from mechanisms.

Can language models (LMs) learn to faithfully describe their internal computations? Are they better able to describe themselves than other models? We study the extent to which LMs' privileged access to their own internals can be leveraged to produce new techniques for explaining their behavior. Using existing interpretability techniques as a source of ground truth, we fine-tune LMs to generate natural language descriptions of (1) the information encoded by LM features, (2) the causal structure of LMs' internal activations, and (3) the influence of specific input tokens on LM outputs. When trained with only tens of thousands of example explanations, explainer models exhibit non-trivial generalization to new queries. This generalization appears partly attributable to explainer models' privileged access to their own internals: using a model to explain its own computations generally works better than using a *different* model to explain its computations (even if the other model is significantly more capable). Our results suggest not only that LMs can learn to reliably explain their internal computations, but that such explanations offer a scalable complement to existing interpretability methods.

Inspecting the information encoded in hidden representations of large language models (LLMs) can explain models' behavior and verify their alignment with human values. Given the capabilities of LLMs in generating human-understandable text, we propose leveraging the model itself to explain its internal representations in natural language. We introduce a framework called Patchscopes and show how it can be used to answer a wide range of research questions about an LLM's computation. We show that prior interpretability methods based on projecting representations into the vocabulary space and intervening on the LLM computation, can be viewed as special instances of this framework. Moreover, several of their shortcomings such as failure in inspecting early layers or lack of expressivity can be mitigated by a Patchscope. Beyond unifying prior inspection techniques, Patchscopes also opens up new possibilities such as using a more capable model to explain the representations of a smaller model, and unlocks new applications such as self-correction in multi-hop reasoning.

The fields of explainable AI and mechanistic interpretability aim to uncover the internal structure of neural networks, with circuit discovery as a central tool for understanding model computations. Existing approaches, however, rely on manual inspection and remain limited to toy tasks. Automated interpretability offers scalability by analyzing isolated features and their activations, but it often misses interactions between features and depends strongly on external LLMs and dataset quality. Transcoders have recently made it possible to separate feature attributions into input-dependent and input-invariant components, providing a foundation for more systematic circuit analysis. Building on this, we propose WeightLens and CircuitLens, two complementary methods that go beyond activation-based analysis. WeightLens interprets features directly from their learned weights, removing the need for explainer models or datasets while matching or exceeding the performance of existing methods on context-independent features. CircuitLens captures how feature activations arise from interactions between components, revealing circuit-level dynamics that activation-only approaches cannot identify. Together, these methods increase interpretability robustness and enhance scalable mechanistic analysis of circuits while maintaining efficiency and quality.

Latent reasoning models (LRMs) have attracted significant research interest due to their low inference cost (relative to explicit reasoning models) and theoretical ability to explore multiple reasoning paths in parallel. However, these benefits come at the cost of reduced interpretability: LRMs are difficult to monitor because they do not reason in natural language. This paper presents an investigation into LRM interpretability by examining two state-of-the-art LRMs. First, we find that latent reasoning tokens are often unnecessary for LRMs' predictions; on logical reasoning datasets, LRMs can almost always produce the same final answers without using latent reasoning at all. This underutilization of reasoning tokens may partially explain why LRMs do not consistently outperform explicit reasoning methods and raises doubts about the stated role of these tokens in prior work. Second, we demonstrate that when latent reasoning tokens are necessary for performance, we can decode gold reasoning traces up to 65-93% of the time for correctly predicted instances. This suggests LRMs often implement the expected solution rather than an uninterpretable reasoning process. Finally, we present a method to decode a verified natural language reasoning trace from latent tokens without knowing a gold reasoning trace a priori, demonstrating that it is possible to find a verified trace for a majority of correct predictions but only a minority of incorrect predictions. Our findings highlight that current LRMs largely encode interpretable processes, and interpretability itself can be a signal of prediction correctness.

We present a method for diagnosing interpretation in neural networks by identifying an input subspace where a proposed interpretation is highly faithful. Our method is particularly useful for causal-abstraction-style interpretability, where a high-level causal hypothesis is evaluated by interchange interventions. Rather than treating interchange intervention accuracy as a single global summary, we refine this framework by partitioning the input space into well-interpreted and under-interpreted regions according to pairwise interchange-intervention behavior. This turns causal abstraction from a purely global evaluation into a more diagnostic tool: it not only measures whether an interpretation works, but also reveals where it works, where it fails, and what distinguishes the two cases. This diagnostic view also provides practical heuristics for improving interpretations. By analyzing the structure of the well-interpreted and under-interpreted regions, we can identify missing distinctions in a high-level hypothesis, discover previously unmodeled intermediate variables, and combine complementary partial interpretations into a stronger one. We instantiate this idea as a simple four-step recipe and show that it yields informative error analyses across multiple causal abstraction settings. In a toy logic task, recursively applying the recipe recovers a high-level hypothesis from scratch. More broadly, our results suggest that partitioning the input space is a useful step toward more precise, constructive, and scalable mechanistic interpretability.

As large language models (LLMs) grow more powerful, concerns around potential harms like toxicity, unfairness, and hallucination threaten user trust. Ensuring beneficial alignment of LLMs with human values through model alignment is thus critical yet challenging, requiring a deeper understanding of LLM behaviors and mechanisms. We propose opening the black box of LLMs through a framework of holistic interpretability encompassing complementary bottom-up and top-down perspectives. The bottom-up view, enabled by mechanistic interpretability, focuses on component functionalities and training dynamics. The top-down view utilizes representation engineering to analyze behaviors through hidden representations. In this paper, we review the landscape around mechanistic interpretability and representation engineering, summarizing approaches, discussing limitations and applications, and outlining future challenges in using these techniques to achieve ethical, honest, and reliable reasoning aligned with human values.

Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously, large language models (LLMs) have demonstrated remarkable capabilities across a wide array of tasks, offering a chance to rethink opportunities in interpretable machine learning. Notably, the capability to explain in natural language allows LLMs to expand the scale and complexity of patterns that can be given to a human. However, these new capabilities raise new challenges, such as hallucinated explanations and immense computational costs. In this position paper, we start by reviewing existing methods to evaluate the emerging field of LLM interpretation (both interpreting LLMs and using LLMs for explanation). We contend that, despite their limitations, LLMs hold the opportunity to redefine interpretability with a more ambitious scope across many applications, including in auditing LLMs themselves. We highlight two emerging research priorities for LLM interpretation: using LLMs to directly analyze new datasets and to generate interactive explanations.

A key goal of current mechanistic interpretability research in NLP is to find linear features (also called "feature vectors") for transformers: directions in activation space corresponding to concepts that are used by a given model in its computation. Present state-of-the-art methods for finding linear features require large amounts of labelled data -- both laborious to acquire and computationally expensive to utilize. In this work, we introduce a novel method, called "observable propagation" (in short: ObsProp), for finding linear features used by transformer language models in computing a given task -- using almost no data. Our paradigm centers on the concept of observables, linear functionals corresponding to given tasks. We then introduce a mathematical theory for the analysis of feature vectors: we provide theoretical motivation for why LayerNorm nonlinearities do not affect the direction of feature vectors; we also introduce a similarity metric between feature vectors called the coupling coefficient which estimates the degree to which one feature's output correlates with another's. We use ObsProp to perform extensive qualitative investigations into several tasks, including gendered occupational bias, political party prediction, and programming language detection. Our results suggest that ObsProp surpasses traditional approaches for finding feature vectors in the low-data regime, and that ObsProp can be used to better understand the mechanisms responsible for bias in large language models. Code for experiments can be found at github.com/jacobdunefsky/ObservablePropagation.

Interpretability research aims to bridge the gap between empirical success and our scientific understanding of the inner workings of large language models (LLMs). However, most existing research focuses on analyzing a single mechanism, such as how models copy or recall factual knowledge. In this work, we propose a formulation of competition of mechanisms, which focuses on the interplay of multiple mechanisms instead of individual mechanisms and traces how one of them becomes dominant in the final prediction. We uncover how and where mechanisms compete within LLMs using two interpretability methods: logit inspection and attention modification. Our findings show traces of the mechanisms and their competition across various model components and reveal attention positions that effectively control the strength of certain mechanisms. Code: https://github.com/francescortu/comp-mech. Data: https://huggingface.co/datasets/francescortu/comp-mech.

Contemporary predictive models are hard to interpret as their deep nets exploit numerous complex relations between input elements. This work suggests a theoretical framework for model interpretability by measuring the contribution of relevant features to the functional entropy of the network with respect to the input. We rely on the log-Sobolev inequality that bounds the functional entropy by the functional Fisher information with respect to the covariance of the data. This provides a principled way to measure the amount of information contribution of a subset of features to the decision function. Through extensive experiments, we show that our method surpasses existing interpretability sampling-based methods on various data signals such as image, text, and audio.

Interpretability is essential for machine learning models to be trusted and deployed in critical domains. However, existing methods for interpreting text models are often complex, lack mathematical foundations, and their performance is not guaranteed. In this paper, we propose FRED (Faithful and Robust Explainer for textual Documents), a novel method for interpreting predictions over text. FRED offers three key insights to explain a model prediction: (1) it identifies the minimal set of words in a document whose removal has the strongest influence on the prediction, (2) it assigns an importance score to each token, reflecting its influence on the model's output, and (3) it provides counterfactual explanations by generating examples similar to the original document, but leading to a different prediction. We establish the reliability of FRED through formal definitions and theoretical analyses on interpretable classifiers. Additionally, our empirical evaluation against state-of-the-art methods demonstrates the effectiveness of FRED in providing insights into text models.

Recent advances in Large Multimodal Models (LMMs) lead to significant breakthroughs in both academia and industry. One question that arises is how we, as humans, can understand their internal neural representations. This paper takes an initial step towards addressing this question by presenting a versatile framework to identify and interpret the semantics within LMMs. Specifically, 1) we first apply a Sparse Autoencoder(SAE) to disentangle the representations into human understandable features. 2) We then present an automatic interpretation framework to interpreted the open-semantic features learned in SAE by the LMMs themselves. We employ this framework to analyze the LLaVA-NeXT-8B model using the LLaVA-OV-72B model, demonstrating that these features can effectively steer the model's behavior. Our results contribute to a deeper understanding of why LMMs excel in specific tasks, including EQ tests, and illuminate the nature of their mistakes along with potential strategies for their rectification. These findings offer new insights into the internal mechanisms of LMMs and suggest parallels with the cognitive processes of the human brain.

Interpretable graph learning is in need as many scientific applications depend on learning models to collect insights from graph-structured data. Previous works mostly focused on using post-hoc approaches to interpret pre-trained models (graph neural networks in particular). They argue against inherently interpretable models because the good interpretability of these models is often at the cost of their prediction accuracy. However, those post-hoc methods often fail to provide stable interpretation and may extract features that are spuriously correlated with the task. In this work, we address these issues by proposing Graph Stochastic Attention (GSAT). Derived from the information bottleneck principle, GSAT injects stochasticity to the attention weights to block the information from task-irrelevant graph components while learning stochasticity-reduced attention to select task-relevant subgraphs for interpretation. The selected subgraphs provably do not contain patterns that are spuriously correlated with the task under some assumptions. Extensive experiments on eight datasets show that GSAT outperforms the state-of-the-art methods by up to 20%uparrow in interpretation AUC and 5%uparrow in prediction accuracy. Our code is available at https://github.com/Graph-COM/GSAT.

In this paper we introduce a novel, unified, open-source model interpretability library for PyTorch [12]. The library contains generic implementations of a number of gradient and perturbation-based attribution algorithms, also known as feature, neuron and layer importance algorithms, as well as a set of evaluation metrics for these algorithms. It can be used for both classification and non-classification models including graph-structured models built on Neural Networks (NN). In this paper we give a high-level overview of supported attribution algorithms and show how to perform memory-efficient and scalable computations. We emphasize that the three main characteristics of the library are multimodality, extensibility and ease of use. Multimodality supports different modality of inputs such as image, text, audio or video. Extensibility allows adding new algorithms and features. The library is also designed for easy understanding and use. Besides, we also introduce an interactive visualization tool called Captum Insights that is built on top of Captum library and allows sample-based model debugging and visualization using feature importance metrics.

Deep learning models have achieved remarkable success in different areas of machine learning over the past decade; however, the size and complexity of these models make them difficult to understand. In an effort to make them more interpretable, several recent works focus on explaining parts of a deep neural network through human-interpretable, semantic attributes. However, it may be impossible to completely explain complex models using only semantic attributes. In this work, we propose to augment these attributes with a small set of uninterpretable features. Specifically, we develop a novel explanation framework ELUDE (Explanation via Labelled and Unlabelled DEcomposition) that decomposes a model's prediction into two parts: one that is explainable through a linear combination of the semantic attributes, and another that is dependent on the set of uninterpretable features. By identifying the latter, we are able to analyze the "unexplained" portion of the model, obtaining insights into the information used by the model. We show that the set of unlabelled features can generalize to multiple models trained with the same feature space and compare our work to two popular attribute-oriented methods, Interpretable Basis Decomposition and Concept Bottleneck, and discuss the additional insights ELUDE provides.

Artificial Text Detection (ATD) is becoming increasingly important with the rise of advanced Large Language Models (LLMs). Despite numerous efforts, no single algorithm performs consistently well across different types of unseen text or guarantees effective generalization to new LLMs. Interpretability plays a crucial role in achieving this goal. In this study, we enhance ATD interpretability by using Sparse Autoencoders (SAE) to extract features from Gemma-2-2b residual stream. We identify both interpretable and efficient features, analyzing their semantics and relevance through domain- and model-specific statistics, a steering approach, and manual or LLM-based interpretation. Our methods offer valuable insights into how texts from various models differ from human-written content. We show that modern LLMs have a distinct writing style, especially in information-dense domains, even though they can produce human-like outputs with personalized prompts.

Mechanistic interpretability seeks to reverse-engineer neural network computations into human-understandable algorithms, yet extracting sparse computational circuits from billion-parameter language models remains challenging due to exponential search complexity and pervasive polysemanticity. The proposed Hierarchical Attribution Graph Decomposition (HAGD) framework reduces circuit discovery complexity from O(2^n) exhaustive enumeration to O(n^2 log n) through multi-resolution abstraction hierarchies and differentiable circuit search. The methodology integrates cross-layer transcoders for monosemantic feature extraction, graph neural network meta-learning for topology prediction, and causal intervention protocols for validation. Empirical evaluation spans GPT-2 variants, Llama-7B through Llama-70B, and Pythia suite models across algorithmic tasks and natural language benchmarks. On modular arithmetic tasks, the framework achieves up to 91% behavioral preservation (pm2.3\% across runs) while maintaining interpretable subgraph sizes. Cross-architecture transfer experiments suggest that discovered circuits exhibit moderate structural similarity (averaging 67%) across model families, indicating potential shared computational patterns. These results provide preliminary foundations for interpretability at larger model scales while identifying significant limitations in current attribution methodologies that require future advances.

Individual neurons participate in the representation of multiple high-level concepts. To what extent can different interpretability methods successfully disentangle these roles? To help address this question, we introduce RAVEL (Resolving Attribute-Value Entanglements in Language Models), a dataset that enables tightly controlled, quantitative comparisons between a variety of existing interpretability methods. We use the resulting conceptual framework to define the new method of Multi-task Distributed Alignment Search (MDAS), which allows us to find distributed representations satisfying multiple causal criteria. With Llama2-7B as the target language model, MDAS achieves state-of-the-art results on RAVEL, demonstrating the importance of going beyond neuron-level analyses to identify features distributed across activations. We release our benchmark at https://github.com/explanare/ravel.

A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language models difficult. In particular, interpretable features -- such as those found by sparse autoencoders (SAEs) -- are typically linear combinations of extremely many neurons, each with its own nonlinearity to account for. Circuit analysis in this setting thus either yields intractably large circuits or fails to disentangle local and global behavior. To address this we explore transcoders, which seek to faithfully approximate a densely activating MLP layer with a wider, sparsely-activating MLP layer. We successfully train transcoders on language models with 120M, 410M, and 1.4B parameters, and find them to perform at least on par with SAEs in terms of sparsity, faithfulness, and human-interpretability. We then introduce a novel method for using transcoders to perform weights-based circuit analysis through MLP sublayers. The resulting circuits neatly factorize into input-dependent and input-invariant terms. Finally, we apply transcoders to reverse-engineer unknown circuits in the model, and we obtain novel insights regarding the greater-than circuit in GPT2-small. Our results suggest that transcoders can prove effective in decomposing model computations involving MLPs into interpretable circuits. Code is available at https://github.com/jacobdunefsky/transcoder_circuits.

Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE architectures are primarily adopted for computational efficiency, it remains an open question whether their sparsity makes them inherently easier to interpret than dense feed-forward networks (FFNs). We compare MoE experts and dense FFNs using k-sparse probing and find that expert neurons are consistently less polysemantic, with the gap widening as routing becomes sparser. This suggests that sparsity pressures both individual neurons and entire experts toward monosemanticity. Leveraging this finding, we zoom out from the neuron to the expert level as a more effective unit of analysis. We validate this approach by automatically interpreting hundreds of experts. This analysis allows us to resolve the debate on specialization: experts are neither broad domain specialists (e.g., biology) nor simple token-level processors. Instead, they function as fine-grained task experts, specializing in linguistic operations or semantic tasks (e.g., closing brackets in LaTeX). Our findings suggest that MoEs are inherently interpretable at the expert level, providing a clearer path toward large-scale model interpretability. Code is available at: https://github.com/jerryy33/MoE_analysis

Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires that the learned features be both interpretable and steerable. To that end, we introduce two new computationally inexpensive interpretability and steerability metrics and conduct a systematic analysis on LVLMs. Our analysis uncovers two observations; (i) a majority of SAE neurons exhibit either low interpretability or low steerability or both, rendering them ineffective for downstream use; and (ii) due to the unsupervised nature of SAEs, user-desired concepts are often absent in the learned dictionary, thus limiting their practical utility. To address these limitations, we propose Concept Bottleneck Sparse Autoencoders (CB-SAE) - a novel post-hoc framework that prunes low-utility neurons and augments the latent space with a lightweight concept bottleneck aligned to a user-defined concept set. The resulting CB-SAE improves interpretability by +32.1% and steerability by +14.5% across LVLMs and image generation tasks. We will make our code and model weights available.

The increasing success of deep neural networks has raised concerns about their inherent black-box nature, posing challenges related to interpretability and trust. While there has been extensive exploration of interpretation techniques in vision and language, interpretability in the audio domain has received limited attention, primarily focusing on post-hoc explanations. This paper addresses the problem of interpretability by-design in the audio domain by utilizing the recently proposed attention-free focal modulation networks (FocalNets). We apply FocalNets to the task of environmental sound classification for the first time and evaluate their interpretability properties on the popular ESC-50 dataset. Our method outperforms a similarly sized vision transformer both in terms of accuracy and interpretability. Furthermore, it is competitive against PIQ, a method specifically designed for post-hoc interpretation in the audio domain.

Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less attention. A recently proposed shared global workspace theory showed that networks of distributed modules can benefit from sharing information with a bottlenecked memory because the communication constraints encourage specialization, compositionality, and synchronization among the modules. Inspired by this, we propose Concept-Centric Transformers, a simple yet effective configuration of the shared global workspace for interpretability, consisting of: i) an object-centric-based memory module for extracting semantic concepts from input features, ii) a cross-attention mechanism between the learned concept and input embeddings, and iii) standard classification and explanation losses to allow human analysts to directly assess an explanation for the model's classification reasoning. We test our approach against other existing concept-based methods on classification tasks for various datasets, including CIFAR100, CUB-200-2011, and ImageNet, and we show that our model achieves better classification accuracy than all baselines across all problems but also generates more consistent concept-based explanations of classification output.

In recent years, many interpretability methods have been proposed to help interpret the internal states of Transformer-models, at different levels of precision and complexity. Here, to analyze encoder-decoder Transformers, we propose a simple, new method: DecoderLens. Inspired by the LogitLens (for decoder-only Transformers), this method involves allowing the decoder to cross-attend representations of intermediate encoder layers instead of using the final encoder output, as is normally done in encoder-decoder models. The method thus maps previously uninterpretable vector representations to human-interpretable sequences of words or symbols. We report results from the DecoderLens applied to models trained on question answering, logical reasoning, speech recognition and machine translation. The DecoderLens reveals several specific subtasks that are solved at low or intermediate layers, shedding new light on the information flow inside the encoder component of this important class of models.

While interpretability research has shed light on some internal algorithms utilized by transformer-based LLMs, reasoning in natural language, with its deep contextuality and ambiguity, defies easy categorization. As a result, formulating clear and motivating questions for circuit analysis that rely on well-defined in-domain and out-of-domain examples required for causal interventions is challenging. Although significant work has investigated circuits for specific tasks, such as indirect object identification (IOI), deciphering natural language reasoning through circuits remains difficult due to its inherent complexity. In this work, we take initial steps to characterize causal reasoning in LLMs by analyzing clear-cut cause-and-effect sentences like "I opened an umbrella because it started raining," where causal interventions may be possible through carefully crafted scenarios using GPT-2 small. Our findings indicate that causal syntax is localized within the first 2-3 layers, while certain heads in later layers exhibit heightened sensitivity to nonsensical variations of causal sentences. This suggests that models may infer reasoning by (1) detecting syntactic cues and (2) isolating distinct heads in the final layers that focus on semantic relationships.

Interpreting the internal reasoning of vision-language models is essential for deploying AI in safety-critical domains. Concept-based explainability provides a human-aligned lens by representing a model's behavior through semantically meaningful components. However, existing methods are largely restricted to images and overlook the cross-modal interactions. Text-image embeddings, such as those produced by CLIP, suffer from a modality gap, where visual and textual features follow distinct distributions, limiting interpretability. Canonical Correlation Analysis (CCA) offers a principled way to align features from different distributions, but has not been leveraged for multi-modal concept-level analysis. We show that the objectives of CCA and InfoNCE are closely related, such that optimizing CCA implicitly optimizes InfoNCE, providing a simple, training-free mechanism to enhance cross-modal alignment without affecting the pre-trained InfoNCE objective. Motivated by this observation, we couple concept-based explainability with CCA, introducing Concept CCA (CoCCA), a framework that aligns cross-modal embeddings while enabling interpretable concept decomposition. We further extend it and propose Sparse Concept CCA (SCoCCA), which enforces sparsity to produce more disentangled and discriminative concepts, facilitating improved activation, ablation, and semantic manipulation. Our approach generalizes concept-based explanations to multi-modal embeddings and achieves state-of-the-art performance in concept discovery, evidenced by reconstruction and manipulation tasks such as concept ablation.

Disentangling model activations into meaningful features is a central problem in interpretability. However, the absence of ground-truth for these features in realistic scenarios makes validating recent approaches, such as sparse dictionary learning, elusive. To address this challenge, we propose a framework for evaluating feature dictionaries in the context of specific tasks, by comparing them against supervised feature dictionaries. First, we demonstrate that supervised dictionaries achieve excellent approximation, control, and interpretability of model computations on the task. Second, we use the supervised dictionaries to develop and contextualize evaluations of unsupervised dictionaries along the same three axes. We apply this framework to the indirect object identification (IOI) task using GPT-2 Small, with sparse autoencoders (SAEs) trained on either the IOI or OpenWebText datasets. We find that these SAEs capture interpretable features for the IOI task, but they are less successful than supervised features in controlling the model. Finally, we observe two qualitative phenomena in SAE training: feature occlusion (where a causally relevant concept is robustly overshadowed by even slightly higher-magnitude ones in the learned features), and feature over-splitting (where binary features split into many smaller, less interpretable features). We hope that our framework will provide a useful step towards more objective and grounded evaluations of sparse dictionary learning methods.

Labeling neural network submodules with human-legible descriptions is useful for many downstream tasks: such descriptions can surface failures, guide interventions, and perhaps even explain important model behaviors. To date, most mechanistic descriptions of trained networks have involved small models, narrowly delimited phenomena, and large amounts of human labor. Labeling all human-interpretable sub-computations in models of increasing size and complexity will almost certainly require tools that can generate and validate descriptions automatically. Recently, techniques that use learned models in-the-loop for labeling have begun to gain traction, but methods for evaluating their efficacy are limited and ad-hoc. How should we validate and compare open-ended labeling tools? This paper introduces FIND (Function INterpretation and Description), a benchmark suite for evaluating the building blocks of automated interpretability methods. FIND contains functions that resemble components of trained neural networks, and accompanying descriptions of the kind we seek to generate. The functions are procedurally constructed across textual and numeric domains, and involve a range of real-world complexities, including noise, composition, approximation, and bias. We evaluate new and existing methods that use language models (LMs) to produce code-based and language descriptions of function behavior. We find that an off-the-shelf LM augmented with only black-box access to functions can sometimes infer their structure, acting as a scientist by forming hypotheses, proposing experiments, and updating descriptions in light of new data. However, LM-based descriptions tend to capture global function behavior and miss local corruptions. These results show that FIND will be useful for characterizing the performance of more sophisticated interpretability methods before they are applied to real-world models.

Sparse dictionary learning has been a rapidly growing technique in mechanistic interpretability to attack superposition and extract more human-understandable features from model activations. We ask a further question based on the extracted more monosemantic features: How do we recognize circuits connecting the enormous amount of dictionary features? We propose a circuit discovery framework alternative to activation patching. Our framework suffers less from out-of-distribution and proves to be more efficient in terms of asymptotic complexity. The basic unit in our framework is dictionary features decomposed from all modules writing to the residual stream, including embedding, attention output and MLP output. Starting from any logit, dictionary feature or attention score, we manage to trace down to lower-level dictionary features of all tokens and compute their contribution to these more interpretable and local model behaviors. We dig in a small transformer trained on a synthetic task named Othello and find a number of human-understandable fine-grained circuits inside of it.

We propose a novel interpretation technique to explain the behavior of structured output models, which learn mappings between an input vector to a set of output variables simultaneously. Because of the complex relationship between the computational path of output variables in structured models, a feature can affect the value of output through other ones. We focus on one of the outputs as the target and try to find the most important features utilized by the structured model to decide on the target in each locality of the input space. In this paper, we assume an arbitrary structured output model is available as a black box and argue how considering the correlations between output variables can improve the explanation performance. The goal is to train a function as an interpreter for the target output variable over the input space. We introduce an energy-based training process for the interpreter function, which effectively considers the structural information incorporated into the model to be explained. The effectiveness of the proposed method is confirmed using a variety of simulated and real data sets.

Large language models follow a lineage of many NLP applications that were directly inspired by distributional semantics, but do not seem to be closely related to it anymore. In this paper, we propose to employ the distributional theory of meaning once again. Using Independent Component Analysis to overcome some of its challenging aspects, we show that large language models represent semantic features in their hidden states.

Recent advancements in NLP systems, particularly with the introduction of LLMs, have led to widespread adoption of these systems by a broad spectrum of users across various domains, impacting decision-making, the job market, society, and scientific research. This surge in usage has led to an explosion in NLP model interpretability and analysis research, accompanied by numerous technical surveys. Yet, these surveys often overlook the needs and perspectives of explanation stakeholders. In this paper, we address three fundamental questions: Why do we need interpretability, what are we interpreting, and how? By exploring these questions, we examine existing interpretability paradigms, their properties, and their relevance to different stakeholders. We further explore the practical implications of these paradigms by analyzing trends from the past decade across multiple research fields. To this end, we retrieved thousands of papers and employed an LLM to characterize them. Our analysis reveals significant disparities between NLP developers and non-developer users, as well as between research fields, underscoring the diverse needs of stakeholders. For example, explanations of internal model components are rarely used outside the NLP field. We hope this paper informs the future design, development, and application of methods that align with the objectives and requirements of various stakeholders.

Mechanistic Interpretability (MI) seeks to explain how neural networks implement their capabilities, but the scale of Large Language Models (LLMs) has limited prior MI work in Machine Translation (MT) to word-level analyses. We study sentence-level MT from a mechanistic perspective by analyzing attention heads to understand how LLMs internally encode and distribute translation functions. We decompose MT into two subtasks: producing text in the target language (i.e. target language identification) and preserving the input sentence's meaning (i.e. sentence equivalence). Across three families of open-source models and 20 translation directions, we find that distinct, sparse sets of attention heads specialize in each subtask. Based on this insight, we construct subtask-specific steering vectors and show that modifying just 1% of the relevant heads enables instruction-free MT performance comparable to instruction-based prompting, while ablating these heads selectively disrupts their corresponding translation functions.

Interpretability research now offers a variety of techniques for identifying abstract internal mechanisms in neural networks. Can such techniques be used to predict how models will behave on out-of-distribution examples? In this work, we provide a positive answer to this question. Through a diverse set of language modeling tasks--including symbol manipulation, knowledge retrieval, and instruction following--we show that the most robust features for correctness prediction are those that play a distinctive causal role in the model's behavior. Specifically, we propose two methods that leverage causal mechanisms to predict the correctness of model outputs: counterfactual simulation (checking whether key causal variables are realized) and value probing (using the values of those variables to make predictions). Both achieve high AUC-ROC in distribution and outperform methods that rely on causal-agnostic features in out-of-distribution settings, where predicting model behaviors is more crucial. Our work thus highlights a novel and significant application for internal causal analysis of language models.

In recent years, concept-based approaches have emerged as some of the most promising explainability methods to help us interpret the decisions of Artificial Neural Networks (ANNs). These methods seek to discover intelligible visual 'concepts' buried within the complex patterns of ANN activations in two key steps: (1) concept extraction followed by (2) importance estimation. While these two steps are shared across methods, they all differ in their specific implementations. Here, we introduce a unifying theoretical framework that comprehensively defines and clarifies these two steps. This framework offers several advantages as it allows us: (i) to propose new evaluation metrics for comparing different concept extraction approaches; (ii) to leverage modern attribution methods and evaluation metrics to extend and systematically evaluate state-of-the-art concept-based approaches and importance estimation techniques; (iii) to derive theoretical guarantees regarding the optimality of such methods. We further leverage our framework to try to tackle a crucial question in explainability: how to efficiently identify clusters of data points that are classified based on a similar shared strategy. To illustrate these findings and to highlight the main strategies of a model, we introduce a visual representation called the strategic cluster graph. Finally, we present https://serre-lab.github.io/Lens, a dedicated website that offers a complete compilation of these visualizations for all classes of the ImageNet dataset.

Interpretability methods have recently gained significant attention, particularly in the context of large language models, enabling insights into linguistic representations, error detection, and model behaviors such as hallucinations and repetitions. However, these techniques remain underexplored in automatic speech recognition (ASR), despite their potential to advance both the performance and interpretability of ASR systems. In this work, we adapt and systematically apply established interpretability methods such as logit lens, linear probing, and activation patching, to examine how acoustic and semantic information evolves across layers in ASR systems. Our experiments reveal previously unknown internal dynamics, including specific encoder-decoder interactions responsible for repetition hallucinations and semantic biases encoded deep within acoustic representations. These insights demonstrate the benefits of extending and applying interpretability techniques to speech recognition, opening promising directions for future research on improving model transparency and robustness.

Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. However, the lack of interpretability due to their ``black-box'' nature poses challenges for responsible implementation. Although previous studies have attempted to improve interpretability by using, e.g., attention weights in self-attention layers, these weights often lack clarity, readability, and intuitiveness. In this research, we propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans. For example, we learn the concept of ``Food'' and investigate how it influences the prediction of a model's sentiment towards a restaurant review. We introduce C^3M, which combines human-annotated and machine-generated concepts to extract hidden neurons designed to encapsulate semantically meaningful and task-specific concepts. Through empirical evaluations on real-world datasets, we manifest that our approach offers valuable insights to interpret PLM behavior, helps diagnose model failures, and enhances model robustness amidst noisy concept labels.

Mechanistic interpretability aims to understand neural networks by identifying which learned features mediate specific behaviors. Attribution graphs reveal these feature pathways, but interpreting them requires extensive manual analysis -- a single prompt can take approximately 2 hours for an experienced circuit tracer. We present probe prompting, an automated pipeline that transforms attribution graphs into compact, interpretable subgraphs built from concept-aligned supernodes. Starting from a seed prompt and target logit, we select high-influence features, generate concept-targeted yet context-varying probes, and group features by cross-prompt activation signatures into Semantic, Relationship, and Say-X categories using transparent decision rules. Across five prompts including classic "capitals" circuits, probe-prompted subgraphs preserve high explanatory coverage while compressing complexity (Completeness 0.83, mean across circuits; Replacement 0.54). Compared to geometric clustering baselines, concept-aligned groups exhibit higher behavioral coherence: 2.3x higher peak-token consistency (0.425 vs 0.183) and 5.8x higher activation-pattern similarity (0.762 vs 0.130), despite lower geometric compactness. Entity-swap tests reveal a layerwise hierarchy: early-layer features transfer robustly (64% transfer rate, mean layer 6.3), while late-layer Say-X features specialize for output promotion (mean layer 16.4), supporting a backbone-and-specialization view of transformer computation. We release code (https://github.com/peppinob-ol/attribution-graph-probing), an interactive demo (https://huggingface.co/spaces/Peppinob/attribution-graph-probing), and minimal artifacts enabling immediate reproduction and community adoption.

Large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks. However, their rapid proliferation and increasing opaqueness have created a growing need for interpretability. Here, we ask whether we can automatically obtain natural language explanations for black box text modules. A "text module" is any function that maps text to a scalar continuous value, such as a submodule within an LLM or a fitted model of a brain region. "Black box" indicates that we only have access to the module's inputs/outputs. We introduce Summarize and Score (SASC), a method that takes in a text module and returns a natural language explanation of the module's selectivity along with a score for how reliable the explanation is. We study SASC in 3 contexts. First, we evaluate SASC on synthetic modules and find that it often recovers ground truth explanations. Second, we use SASC to explain modules found within a pre-trained BERT model, enabling inspection of the model's internals. Finally, we show that SASC can generate explanations for the response of individual fMRI voxels to language stimuli, with potential applications to fine-grained brain mapping. All code for using SASC and reproducing results is made available on Github.

Convolutional neural network (CNN) models for computer vision are powerful but lack explainability in their most basic form. This deficiency remains a key challenge when applying CNNs in important domains. Recent work on explanations through feature importance of approximate linear models has moved from input-level features (pixels or segments) to features from mid-layer feature maps in the form of concept activation vectors (CAVs). CAVs contain concept-level information and could be learned via clustering. In this work, we rethink the ACE algorithm of Ghorbani et~al., proposing an alternative invertible concept-based explanation (ICE) framework to overcome its shortcomings. Based on the requirements of fidelity (approximate models to target models) and interpretability (being meaningful to people), we design measurements and evaluate a range of matrix factorization methods with our framework. We find that non-negative concept activation vectors (NCAVs) from non-negative matrix factorization provide superior performance in interpretability and fidelity based on computational and human subject experiments. Our framework provides both local and global concept-level explanations for pre-trained CNN models.

While mechanistic interpretability has developed powerful tools to analyze the internal workings of Large Language Models (LLMs), their complexity has created an accessibility gap, limiting their use to specialists. We address this challenge by designing, building, and evaluating ELIA (Explainable Language Interpretability Analysis), an interactive web application that simplifies the outcomes of various language model component analyses for a broader audience. The system integrates three key techniques -- Attribution Analysis, Function Vector Analysis, and Circuit Tracing -- and introduces a novel methodology: using a vision-language model to automatically generate natural language explanations (NLEs) for the complex visualizations produced by these methods. The effectiveness of this approach was empirically validated through a mixed-methods user study, which revealed a clear preference for interactive, explorable interfaces over simpler, static visualizations. A key finding was that the AI-powered explanations helped bridge the knowledge gap for non-experts; a statistical analysis showed no significant correlation between a user's prior LLM experience and their comprehension scores, suggesting that the system reduced barriers to comprehension across experience levels. We conclude that an AI system can indeed simplify complex model analyses, but its true power is unlocked when paired with thoughtful, user-centered design that prioritizes interactivity, specificity, and narrative guidance.

Recent work has proposed the linear representation hypothesis: that language models perform computation by manipulating one-dimensional representations of concepts ("features") in activation space. In contrast, we explore whether some language model representations may be inherently multi-dimensional. We begin by developing a rigorous definition of irreducible multi-dimensional features based on whether they can be decomposed into either independent or non-co-occurring lower-dimensional features. Motivated by these definitions, we design a scalable method that uses sparse autoencoders to automatically find multi-dimensional features in GPT-2 and Mistral 7B. These auto-discovered features include strikingly interpretable examples, e.g. circular features representing days of the week and months of the year. We identify tasks where these exact circles are used to solve computational problems involving modular arithmetic in days of the week and months of the year. Finally, we provide evidence that these circular features are indeed the fundamental unit of computation in these tasks with intervention experiments on Mistral 7B and Llama 3 8B, and we find further circular representations by breaking down the hidden states for these tasks into interpretable components.

Two prominent challenges in explainability research involve 1) the nuanced evaluation of explanations and 2) the modeling of missing information through baseline representations. The existing literature introduces diverse evaluation metrics, each scrutinizing the quality of explanations through distinct lenses. Additionally, various baseline representations have been proposed, each modeling the notion of missingness differently. Yet, a consensus on the ultimate evaluation metric and baseline representation remains elusive. This work acknowledges the diversity in explanation metrics and baselines, demonstrating that different metrics exhibit preferences for distinct explanation maps resulting from the utilization of different baseline representations and distributions. To address the diversity in metrics and accommodate the variety of baseline representations in a unified manner, we propose Baseline Exploration-Exploitation (BEE) - a path-integration method that introduces randomness to the integration process by modeling the baseline as a learned random tensor. This tensor follows a learned mixture of baseline distributions optimized through a contextual exploration-exploitation procedure to enhance performance on the specific metric of interest. By resampling the baseline from the learned distribution, BEE generates a comprehensive set of explanation maps, facilitating the selection of the best-performing explanation map in this broad set for the given metric. Extensive evaluations across various model architectures showcase the superior performance of BEE in comparison to state-of-the-art explanation methods on a variety of objective evaluation metrics.

A central idea in mechanistic interpretability is that neural networks represent more features than they have dimensions, arranging them in superposition to form an over-complete basis. This framing has been influential, motivating dictionary learning approaches such as sparse autoencoders. However, superposition has mostly been studied in idealized settings where features are sparse and uncorrelated. In these settings, superposition is typically understood as introducing interference that must be minimized geometrically and filtered out by non-linearities such as ReLUs, yielding local structures like regular polytopes. We show that this account is incomplete for realistic data by introducing Bag-of-Words Superposition (BOWS), a controlled setting to encode binary bag-of-words representations of internet text in superposition. Using BOWS, we find that when features are correlated, interference can be constructive rather than just noise to be filtered out. This is achieved by arranging features according to their co-activation patterns, making interference between active features constructive, while still using ReLUs to avoid false positives. We show that this kind of arrangement is more prevalent in models trained with weight decay and naturally gives rise to semantic clusters and cyclical structures which have been observed in real language models yet were not explained by the standard picture of superposition. Code for this paper can be found at https://github.com/LucasPrietoAl/correlations-feature-geometry.

Interpreting and explaining the behavior of deep neural networks is critical for many tasks. Explainable AI provides a way to address this challenge, mostly by providing per-pixel relevance to the decision. Yet, interpreting such explanations may require expert knowledge. Some recent attempts toward interpretability adopt a concept-based framework, giving a higher-level relationship between some concepts and model decisions. This paper proposes Bottleneck Concept Learner (BotCL), which represents an image solely by the presence/absence of concepts learned through training over the target task without explicit supervision over the concepts. It uses self-supervision and tailored regularizers so that learned concepts can be human-understandable. Using some image classification tasks as our testbed, we demonstrate BotCL's potential to rebuild neural networks for better interpretability. Code is available at https://github.com/wbw520/BotCL and a simple demo is available at https://botcl.liangzhili.com/.

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models specialize in specific semantic or visual attributes. Building on an established interpretability method, we reinterpret the practice of probing intermediate activations with the final decoding layer through the lens of signal processing. This lets us analyze multiple samples in a principled way and rank attention heads based on their relevance to target concepts. Our results show consistent patterns of specialization at the head level across both unimodal and multimodal transformers. Remarkably, we find that editing as few as 1% of the heads, selected using our method, can reliably suppress or enhance targeted concepts in the model output. We validate our approach on language tasks such as question answering and toxicity mitigation, as well as vision-language tasks including image classification and captioning. Our findings highlight an interpretable and controllable structure within attention layers, offering simple tools for understanding and editing large-scale generative models.

Automated interpretability pipelines generate natural language descriptions for the concepts represented by features in large language models (LLMs), such as plants or the first word in a sentence. These descriptions are derived using inputs that activate the feature, which may be a dimension or a direction in the model's representation space. However, identifying activating inputs is costly, and the mechanistic role of a feature in model behavior is determined both by how inputs cause a feature to activate and by how feature activation affects outputs. Using steering evaluations, we reveal that current pipelines provide descriptions that fail to capture the causal effect of the feature on outputs. To fix this, we propose efficient, output-centric methods for automatically generating feature descriptions. These methods use the tokens weighted higher after feature stimulation or the highest weight tokens after applying the vocabulary "unembedding" head directly to the feature. Our output-centric descriptions better capture the causal effect of a feature on model outputs than input-centric descriptions, but combining the two leads to the best performance on both input and output evaluations. Lastly, we show that output-centric descriptions can be used to find inputs that activate features previously thought to be "dead".

Research in mechanistic interpretability seeks to explain behaviors of machine learning models in terms of their internal components. However, most previous work either focuses on simple behaviors in small models, or describes complicated behaviors in larger models with broad strokes. In this work, we bridge this gap by presenting an explanation for how GPT-2 small performs a natural language task called indirect object identification (IOI). Our explanation encompasses 26 attention heads grouped into 7 main classes, which we discovered using a combination of interpretability approaches relying on causal interventions. To our knowledge, this investigation is the largest end-to-end attempt at reverse-engineering a natural behavior "in the wild" in a language model. We evaluate the reliability of our explanation using three quantitative criteria--faithfulness, completeness and minimality. Though these criteria support our explanation, they also point to remaining gaps in our understanding. Our work provides evidence that a mechanistic understanding of large ML models is feasible, opening opportunities to scale our understanding to both larger models and more complex tasks.

The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs). These agents make visual decisions at scale, deciding what to click, recommend, or buy. Yet, we know little about the structure of their visual preferences. We introduce a framework for studying this by placing VLMs in controlled image-based choice tasks and systematically perturbing their inputs. Our key idea is to treat the agent's decision function as a latent visual utility that can be inferred through revealed preference: choices between systematically edited images. Starting from common images, such as product photos, we propose methods for visual prompt optimization, adapting text optimization methods to iteratively propose and apply visually plausible modifications using an image generation model (such as in composition, lighting, or background). We then evaluate which edits increase selection probability. Through large-scale experiments on frontier VLMs, we demonstrate that optimized edits significantly shift choice probabilities in head-to-head comparisons. We develop an automatic interpretability pipeline to explain these preferences, identifying consistent visual themes that drive selection. We argue that this approach offers a practical and efficient way to surface visual vulnerabilities, safety concerns that might otherwise be discovered implicitly in the wild, supporting more proactive auditing and governance of image-based AI agents.