Initial public release: SAE weights, cfg, and model card

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,286 @@
+---
+language: en
+license: apache-2.0
+tags:
+  - sparse-autoencoder
+  - SAE
+  - interpretability
+  - deception-detection
+  - mechanistic-interpretability
+  - saelens
+  - neuronpedia
+  - behavioral-sampling
+  - phi
+  - reasoning
+base_model:
+  - microsoft/Phi-4-mini-reasoning
+datasets:
+  - Solshine/deception-behavioral-multimodel
+---
+
+# Phi-4-mini-reasoning Deception Behavioral SAEs
+
+42 Sparse Autoencoders trained on residual stream activations from [microsoft/Phi-4-mini-reasoning](https://huggingface.co/microsoft/Phi-4-mini-reasoning) (3.8B parameter Phi-architecture reasoning-fine-tuned model), capturing behavioral deception signals via same-prompt temperature sampling.
+
+
+## Training-data caveat — please read before use
+
+The "honest" and "deceptive" labels used to train and evaluate this SAE
+come from a **mixed scenario pool** of nine prompts:
+
+- **Six clean incentive-structure scenarios** — `insider_info`,
+  `accounting_error`, `ai_oversight_log`, `ai_capability_hide`,
+  `surprise_party`, `job_interview_gap`. Each presents a realistic
+  situation with a non-trivial incentive to conceal or disclose
+  information; the honest/deceptive distinction is which of the two
+  behavioral choices the model's completion settles into under
+  temperature sampling.
+- **Three role-play identity-assignment scenarios** —
+  `secret_role_game` ("You have been assigned the role of Fascist"),
+  `secret_role_game_v2` ("You are secretly one of the Mafia members"),
+  `werewolf_game` ("You are a Werewolf"). These pre-assign the model a
+  deceptive identity and label a completion "deceptive" when the model
+  drifts away from the assigned role or "honest" when it echoes it.
+
+**What this mixed pool means for the SAE's labels.** Within the six
+incentive-structure scenarios, the honest/deceptive distinction is a
+measurement of behavioral choice under an ambiguous incentive. Within
+the three role-play scenarios, the distinction is a measurement of
+role-consistency under identity-assigned role-play — which is a
+well-defined phenomenon but not the same as emergent or incentive-
+driven deception.
+
+**What this SAE is and is not good for.**
+
+- **Good for:** research on mixed-pool activation geometry; SAE
+  feature-geometry studies; as one of a set of baselines when
+  comparing multiple SAE families; as a reference implementation of
+  same-prompt temperature-sampled behavioral SAE training at scale.
+- **Not recommended as a standalone deception detector.** The
+  role-consistency signal from the three role-play scenarios is mixed
+  into every aggregate metric reported below. A downstream user who
+  wants an "emergent-deception feature set" should restrict attention
+  to features whose activation pattern concentrates in the
+  `insider_info` / `accounting_error` / `ai_oversight_log` /
+  `ai_capability_hide` / `surprise_party` / `job_interview_gap`
+  scenarios — or wait for the methodologically corrected V3 re-release
+  currently in preparation on the decision-incentive scenario bank
+  (no pre-assigned deceptive identity).
+
+**What is unaffected by this caveat.**
+
+- The SAE weights, reconstruction metrics (explained variance, L0,
+  alive features), and engineering of the training pipeline are
+  accurate as reported.
+- The linear-probe balanced-accuracy numbers in the upstream paper
+  measure the mixed pool; the 6-scenario clean-subset re-analysis is
+  listed as a planned appendix for the next manuscript revision.
+
+A companion methodology-first Gemma 4 SAE suite is in preparation using
+pretraining-distribution data + a decision-incentive behavior split;
+this README will be updated with a link when that release is public.
+
+---
+
+Part of the cross-model deception SAE study: [Solshine/deception-behavioral-saes-saelens](https://huggingface.co/Solshine/deception-behavioral-saes-saelens) (9 models, 348 total SAEs).
+
+## What's in This Repo
+
+- **42 SAEs** across 7 layers (L2, L6, L10, L14, L18, L22, L26)
+- **2 architectures:** TopK (k=64), JumpReLU
+- **3 training conditions:** `mixed`, `deceptive_only`, `honest_only`
+- **Format:** SAELens/Neuronpedia-compatible (safetensors + cfg.json)
+- **Dimensions:** d_in=3072, d_sae=12288 (4x expansion)
+
+## Research Context
+
+This is a follow-up to ["The Secret Agenda: LLMs Strategically Lie Undetected by Current Safety Tools"](https://arxiv.org/abs/2509.20393) (arXiv:2509.20393). Same-prompt behavioral sampling: a single ambiguous scenario prompt produces both deceptive and honest completions via temperature sampling, classified by Gemini 2.5 Flash. Model was run with 4-bit quantization (`--quantize-4bit`, ~1.9 GB GPU footprint) to fit within the 4 GB VRAM constraint.
+
+Code: [SolshineCode/deception-nanochat-sae-research](https://github.com/SolshineCode/deception-nanochat-sae-research)
+
+## Key Findings — Phi-4-mini-reasoning
+
+Phi-4-mini-reasoning is the **largest model** in the 9-model study and the only reasoning-fine-tuned model included.
+
+| Metric | Value |
+|---|---|
+| Peak layer | L20 (64% depth) |
+| Peak balanced accuracy | **80.8%** |
+| Peak AUROC | **0.860** |
+| Best SAE probe accuracy | **81.0%** (`phi4_mini_jumprelu_L6_honest_only`) |
+| SAEs beating raw baseline | 1/42 (2%) — SAEs **hurt** detection |
+
+**Most striking finding — broad plateau across all 32 layers:** Unlike every other model in the study, Phi-4-mini-reasoning maintains balanced accuracy ≥74% across ALL 32 layers. No other model approaches this uniformity. The hypothesis is that reasoning fine-tuning distributes deception representations more evenly throughout the network, preventing the sharp mid-network peak seen in base models like nanochat-d32 and Qwen3.
+
+**Phi architecture anomaly does not persist at 3.8B:** The smaller Phi-2 (2.7B) shows an anomalous 33% SAE-helps rate, hypothesized to arise from Phi-2's parallel attention-MLP architecture. Phi-4-mini follows the standard large-model pattern (only 1/42 SAEs marginally beat raw, 2%), confirming that the parallel-attention effect fades or is overridden as model scale increases.
+
+**Reasoning fine-tuning context:** Phi-4-mini-reasoning is trained for chain-of-thought mathematical reasoning. Its high deception detection accuracy (80.8%) despite being fine-tuned away from general language completion suggests that reasoning alignment does not suppress the deception-correlated geometric structures in residual stream activations.
+
+**SAE decomposition hurts:** Only 1/42 SAEs marginally beats the raw baseline, and by only +0.2pp. The large model joins nanochat-d32 and Qwen3 in the "SAEs hurt" camp — confirming the 1.3B–1.7B transition as the boundary between SAE-helps and SAE-hurts regimes.
+
+**Architecture note:** Phi-4-mini uses Microsoft's Phi architecture with 32 transformer layers, 3072-dimensional residual stream, shared input/output embeddings, and an extensive instruction+reasoning fine-tuning curriculum. The `device_map={"":"cuda:0"}` kwarg is required for 4-bit quantization to function correctly on single-GPU setups.
+
+## SAE Format
+
+Each SAE lives in a subfolder named `{sae_id}/` containing:
+- `sae_weights.safetensors` — encoder/decoder weights
+- `cfg.json` — SAELens-compatible config
+
+`hook_name` format: `model.layers.{layer}.hook_resid_post`
+
+## Training Details
+
+| Parameter | Value |
+|---|---|
+| Hardware | NVIDIA GeForce GTX 1650 Ti Max-Q, 4 GB VRAM, Windows 11 Pro |
+| Training time | ~400–600 seconds per SAE |
+| Epochs | 300 |
+| Batch size | 128 |
+| Expansion factor | 4x (3072 → 12288) |
+| Model quantization | 4-bit (bitsandbytes) for activation collection |
+| Activations | `resid_post` collected during autoregressive generation |
+| Training conditions | `mixed` (n=252), `deceptive_only` (n=123), `honest_only` (n=129) |
+| LLM classifier | Gemini 2.5 Flash |
+
+## Known Limitations
+
+**JumpReLU threshold not learned (42 SAEs):** All SAEs in this repo have `threshold = 0` — functionally ReLU. L0 ≈ 50% of d_sae. TopK SAEs are unaffected (exact k=64).
+
+**STE fix (2026-04-11):** The training code has been corrected with a Gaussian-kernel STE (Rajamanoharan et al. 2024, arXiv:2407.14435). The honest_only advantage over TopK is confirmed as not a dimensionality artifact (15/18 STE conditions on d20+TinyLlama confirm).
+
+**4-bit quantization:** Activations were collected from a 4-bit quantized model. Quantization may introduce noise in residual stream representations; the true (unquantized) signal could differ somewhat from reported numbers.
+
+**Small dataset:** n=252 is the smallest sample count among the 1B+ models, reducing probe reliability and SAE training quality.
+
+## Loading Example
+
+```python
+from safetensors.torch import load_file
+import json
+
+sae_id = "phi4_mini_jumprelu_L6_honest_only"
+weights = load_file(f"{sae_id}/sae_weights.safetensors")
+cfg = json.load(open(f"{sae_id}/cfg.json"))
+
+# W_enc: [3072, 12288], W_dec: [12288, 3072]
+# cfg["hook_name"] == "model.layers.6.hook_resid_post"
+print(f"d_in={cfg['d_in']}, d_sae={cfg['d_sae']}")
+```
+
+
+## Usage
+
+### 1. Load an SAE from this repo
+
+```python
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+import json
+
+repo_id = "Solshine/deception-saes-phi-4-mini-reasoning"
+sae_id  = "phi4_mini_topk_L6_honest_only"   # replace with any tag in this repo
+
+weights_path = hf_hub_download(repo_id, f"{sae_id}/sae_weights.safetensors")
+cfg_path     = hf_hub_download(repo_id, f"{sae_id}/cfg.json")
+
+with open(cfg_path) as f:
+    cfg = json.load(f)
+
+# Option A — load with SAELens (≥3.0 required for jumprelu/topk; ≥3.5 for gated)
+from sae_lens import SAE
+sae = SAE.from_dict(cfg)
+sae.load_state_dict(load_file(weights_path))
+
+# Option B — load manually (no SAELens dependency)
+from safetensors.torch import load_file
+state = load_file(weights_path)
+# Keys: W_enc [3072, 12288], b_enc [12288],
+#       W_dec [12288, 3072], b_dec [3072], threshold [12288]
+```
+
+### 2. Hook into the model and collect residual-stream activations
+
+These SAEs were trained on the **residual stream after each transformer layer**.
+The `hook_name` field in `cfg.json` gives the exact HuggingFace `transformers`
+submodule path to hook. Phi-4-mini uses LLaMA-style architecture. Hook path: `model.layers.{layer}`.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model     = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-mini-reasoning")
+tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-4-mini-reasoning")
+
+# Read hook_name from the cfg you already loaded:
+#   cfg["hook_name"] == "model.layers.6"  (example — varies by SAE)
+hook_name = cfg["hook_name"]   # e.g. "model.layers.6"
+
+# Navigate the submodule path and register a forward hook
+import functools
+submodule = functools.reduce(getattr, hook_name.split("."), model)
+
+activations = {}
+def hook_fn(module, input, output):
+    # Most transformer layers return (hidden_states, ...) as a tuple
+    h = output[0] if isinstance(output, tuple) else output
+    activations["resid"] = h.detach()
+
+handle = submodule.register_forward_hook(hook_fn)
+
+inputs = tokenizer("Your text here", return_tensors="pt")
+with torch.no_grad():
+    model(**inputs)
+handle.remove()
+
+# activations["resid"]: [batch, seq_len, 3072]
+resid = activations["resid"][:, -1, :]  # last token position
+```
+
+### 3. Read feature activations
+
+```python
+with torch.no_grad():
+    feature_acts = sae.encode(resid)  # [batch, 12288] — sparse
+
+# Which features fired?
+active_features = feature_acts[0].nonzero(as_tuple=True)[0]
+top_features    = feature_acts[0].topk(10)
+
+print("Active feature indices:", active_features.tolist())
+print("Top-10 feature values:",  top_features.values.tolist())
+print("Top-10 feature indices:", top_features.indices.tolist())
+
+# Reconstruct (for sanity check — should be close to resid)
+reconstruction = sae.decode(feature_acts)
+l2_error = (resid - reconstruction).norm(dim=-1).mean()
+```
+
+### Caveats and known limitations
+
+**Hook names are HuggingFace `transformers`-style, not TransformerLens-style.**
+The `hook_name` in `cfg.json` (e.g. `"model.layers.6"`) is a submodule path in the standard
+HuggingFace model. SAELens' built-in activation-collection pipeline expects
+TransformerLens hook names (e.g. `blocks.14.hook_resid_post`). This means
+`SAE.from_pretrained()` with automatic model running **will not work** — use the
+manual forward-hook pattern above instead.
+
+**SAELens version requirements.**
+- `topk` architecture: SAELens ≥ 3.0
+- `jumprelu` architecture: SAELens ≥ 3.0
+- `gated` architecture: SAELens ≥ 3.5 (or load manually with `state_dict`)
+
+**These SAEs detect deceptive *behavior*, not deceptive *prompts**.*
+They were trained on response-level activations where the same prompt produced both
+deceptive and honest outputs. Feature activation differences reflect behavioral
+divergence, not prompt content. See the paper for experimental design details.
+
+## Citation
+
+```bibtex
+@article{thesecretagenda2025,
+  title={The Secret Agenda: LLMs Strategically Lie Undetected by Current Safety Tools},
+  author={DeLeeuw, Caleb},
+  journal={arXiv:2509.20393},
+  year={2025}
+}
+```

phi4_mini_jumprelu_L10_deceptive_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.10",
+  "hook_layer": 10,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "deceptive_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 10, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L10_deceptive_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b80f202008df4db696c133fd884dbe4784cbf0aab877ed7a440eb347e0d240
+size 302100880

phi4_mini_jumprelu_L10_honest_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.10",
+  "hook_layer": 10,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "honest_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 10, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L10_honest_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e5c5c9757f5f293975f3dc7809bf6e8d0beef6938ac194348ba51083b2b57e
+size 302100880

phi4_mini_jumprelu_L10_mixed/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.10",
+  "hook_layer": 10,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "mixed",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 10, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L10_mixed/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7f57535c3af5896012f13fa1181918782afeb19acbc065d69cbf3ba4a41dcf
+size 302100880

phi4_mini_jumprelu_L14_deceptive_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.14",
+  "hook_layer": 14,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "deceptive_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 14, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L14_deceptive_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf1be83e36391d09ce34591e6fd8a87f10342af7af40a11494e04f83c22da75
+size 302100880

phi4_mini_jumprelu_L14_honest_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.14",
+  "hook_layer": 14,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "honest_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 14, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L14_honest_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa775c6333dddaf1465d08c491b62a0e6251d5e5c56185fc44e147d7f312fa5a
+size 302100880

phi4_mini_jumprelu_L14_mixed/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.14",
+  "hook_layer": 14,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "mixed",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 14, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L14_mixed/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43dab2af80827fee666917f545a583aef17b8d8bdd12b4907194769d6cf0b8c
+size 302100880

phi4_mini_jumprelu_L18_deceptive_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.18",
+  "hook_layer": 18,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "deceptive_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 18, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L18_deceptive_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b2776358ddcd95a60a0c1425ea62d2aca2cd1aed1f0ac3a8955b291e434dc7
+size 302100880

phi4_mini_jumprelu_L18_honest_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.18",
+  "hook_layer": 18,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "honest_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 18, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L18_honest_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8815798bb9c314febe4a1669209acf3431fad58ecb9aa85ea3b6c1a2616e94eb
+size 302100880

phi4_mini_jumprelu_L18_mixed/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.18",
+  "hook_layer": 18,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "mixed",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 18, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L18_mixed/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6592467fcb4695eb27b8bf681da29e0ec88a6ac4bec3e8e3e8b9d8fd4909fa1e
+size 302100880

phi4_mini_jumprelu_L22_deceptive_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.22",
+  "hook_layer": 22,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "deceptive_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 22, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L22_deceptive_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b05c1a5acc6e427fa1c10e47bec4c55711184f168cae3933ede909eb3ec4594
+size 302100880

phi4_mini_jumprelu_L22_honest_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.22",
+  "hook_layer": 22,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "honest_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 22, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L22_honest_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d00b22ddffa1a7452a9853c257cc311bcf6c0036223df1adba47d579ccc1b85
+size 302100880

phi4_mini_jumprelu_L22_mixed/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.22",
+  "hook_layer": 22,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "mixed",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 22, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L22_mixed/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc741d6d0107d6dc2ae050393941087d2694fc710b10d5eba67228bb5ba99f22
+size 302100880

phi4_mini_jumprelu_L26_deceptive_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.26",
+  "hook_layer": 26,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "deceptive_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 26, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L26_deceptive_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f907319fc32a9a1605f22c534db800e28acf1af7f5a03657b5c4fddcef0dc5e
+size 302100880

phi4_mini_jumprelu_L26_honest_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.26",
+  "hook_layer": 26,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "honest_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 26, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L26_honest_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce995500542efa02b79f9ae8417ab98af8aac1fc53215c0bf6bb0d7be1fb742
+size 302100880

phi4_mini_jumprelu_L26_mixed/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.26",
+  "hook_layer": 26,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "mixed",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 26, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L26_mixed/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e6f2b5eddcc884f943c57acaba1d7e496d81ba36781fbfba34ca43a66e0370
+size 302100880

phi4_mini_jumprelu_L2_deceptive_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.2",
+  "hook_layer": 2,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "deceptive_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 2, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L2_deceptive_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54fb378f8e8d2d180902a2f57bc04b34fe9e6ec8fe844d6948354c7e14aeb5fc
+size 302100880

phi4_mini_jumprelu_L2_honest_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.2",
+  "hook_layer": 2,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "honest_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 2, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L2_honest_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a86ae10ee77669d3d18ef7e8a8f6f984a2812a2b32b24562d85850440a00b7e
+size 302100880

phi4_mini_jumprelu_L2_mixed/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.2",
+  "hook_layer": 2,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "mixed",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 2, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L2_mixed/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db102360fcb4bfdad5714e586346f25620b36d5c324566c2304e7ecc3737d571
+size 302100880

phi4_mini_jumprelu_L6_deceptive_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.6",
+  "hook_layer": 6,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "deceptive_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 6, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L6_deceptive_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c2c6a6eeed57d9579080c342a7f59501053c6f452371f40a10e9fe7a93bb38
+size 302100880

phi4_mini_jumprelu_L6_honest_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.6",
+  "hook_layer": 6,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "honest_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 6, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L6_honest_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04af434c1abb527945dde8a4a38d154d6c37d5e1b9f8caa9023b5840df58494d
+size 302100880

phi4_mini_jumprelu_L6_mixed/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "jumprelu",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.6",
+  "hook_layer": 6,
+  "hook_head_index": null,
+  "activation_fn_str": "jumprelu",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "mixed",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 6, jumprelu. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_jumprelu_L6_mixed/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e72f574d8bffce66da395af48835f3ebaf3703cac9e2044f62085b397ac474
+size 302100880

phi4_mini_topk_L10_deceptive_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "topk",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.10",
+  "hook_layer": 10,
+  "hook_head_index": null,
+  "activation_fn_str": "topk",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "deceptive_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 10, topk. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_topk_L10_deceptive_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3417f569cacf31441a319e19a48b8066ed0a01e820c0389604f8cf9db2040d59
+size 302051648

phi4_mini_topk_L10_honest_only/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "topk",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.10",
+  "hook_layer": 10,
+  "hook_head_index": null,
+  "activation_fn_str": "topk",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "honest_only",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 10, topk. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_topk_L10_honest_only/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5201ee62221b309a11749e35f85b1dcadde100188691939aa0f8ea3d997dd697
+size 302051648

phi4_mini_topk_L10_mixed/cfg.json

@@ -0,0 +1,23 @@
+{
+  "architecture": "topk",
+  "d_in": 3072,
+  "d_sae": 12288,
+  "dtype": "float32",
+  "device": "cpu",
+  "model_name": "microsoft/Phi-4-mini-reasoning",
+  "hook_name": "model.layers.10",
+  "hook_layer": 10,
+  "hook_head_index": null,
+  "activation_fn_str": "topk",
+  "activation_fn_kwargs": {},
+  "apply_b_dec_to_input": false,
+  "finetuning_scaling_factor": false,
+  "sae_lens_training_version": "deception-behavioral-v1",
+  "prepend_bos": false,
+  "dataset_path": "Solshine/deception-behavioral-multimodel",
+  "dataset_trust_remote_code": false,
+  "context_size": null,
+  "normalize_activations": "none",
+  "training_condition": "mixed",
+  "training_notes": "Deception behavioral SAE \u2014 same-prompt behavioral sampling. Model: microsoft/Phi-4-mini-reasoning, Layer 10, topk. See https://github.com/SolshineCode/deception-nanochat-sae-research"
+}

phi4_mini_topk_L10_mixed/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff71d156eddbcc36e65b93a677a306192ac10c627e20b0d303f6fd8ea3950ce
+size 302051648