Upload folder using huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+library_name: sae_lens
+tags:
+  - sparse-autoencoder
+  - mechanistic-interpretability
+  - sae
+---
+
+# Sparse Autoencoders for Qwen/Qwen2.5-7B-Instruct
+
+This repository contains 3 Sparse Autoencoder(s) (SAE) trained using [SAELens](https://github.com/jbloomAus/SAELens).
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| **Base Model** | `Qwen/Qwen2.5-7B-Instruct` |
+| **Architecture** | `standard` |
+| **Input Dimension** | 3584 |
+| **SAE Dimension** | 16384 |
+| **Training Dataset** | `TQRG/DeltaSecommits_qwen-2.5-7b-instruct_tokenized` |
+
+## Available Hook Points
+
+| Hook Point |
+|------------|
+| `blocks.0.hook_resid_post` |
+| `blocks.14.hook_resid_post` |
+| `blocks.27.hook_resid_post` |
+
+## Usage
+
+```python
+from sae_lens import SAE
+
+# Load an SAE for a specific hook point
+sae, cfg_dict, sparsity = SAE.from_pretrained(
+    release="rufimelo/secure_code_qwen_coder_strd_16384",
+    sae_id="blocks.0.hook_resid_post"  # Choose from available hook points above
+)
+
+# Use with TransformerLens
+from transformer_lens import HookedTransformer
+
+model = HookedTransformer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
+
+# Get activations and encode
+_, cache = model.run_with_cache("your text here")
+activations = cache["blocks.0.hook_resid_post"]
+features = sae.encode(activations)
+```
+
+## Files
+
+- `blocks.0.hook_resid_post/cfg.json` - SAE configuration
+- `blocks.0.hook_resid_post/sae_weights.safetensors` - Model weights
+- `blocks.0.hook_resid_post/sparsity.safetensors` - Feature sparsity statistics
+- `blocks.14.hook_resid_post/cfg.json` - SAE configuration
+- `blocks.14.hook_resid_post/sae_weights.safetensors` - Model weights
+- `blocks.14.hook_resid_post/sparsity.safetensors` - Feature sparsity statistics
+- `blocks.27.hook_resid_post/cfg.json` - SAE configuration
+- `blocks.27.hook_resid_post/sae_weights.safetensors` - Model weights
+- `blocks.27.hook_resid_post/sparsity.safetensors` - Feature sparsity statistics
+
+## Training
+
+These SAEs were trained with SAELens version 6.26.2.

blocks.0.hook_resid_post/cfg.json

@@ -0,0 +1 @@
+{"reshape_activations": "none", "normalize_activations": "layer_norm", "metadata": {"sae_lens_version": "6.26.2", "sae_lens_training_version": "6.26.2", "dataset_path": "TQRG/DeltaSecommits_qwen-2.5-7b-instruct_tokenized", "hook_name": "blocks.0.hook_resid_post", "model_name": "Qwen/Qwen2.5-7B-Instruct", "model_class_name": "HookedTransformer", "hook_head_index": null, "context_size": 128, "seqpos_slice": [null, null], "model_from_pretrained_kwargs": {}, "prepend_bos": true, "exclude_special_tokens": false, "sequence_separator_token": "bos", "disable_concat_sequences": false}, "apply_b_dec_to_input": true, "device": "cuda", "d_sae": 16384, "dtype": "float32", "d_in": 3584, "architecture": "standard"}

blocks.0.hook_resid_post/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0d67a15a45b4d5fb88c3c2a5ce3afa76bb12503901d6862731eb230490399c
+size 469842240

blocks.0.hook_resid_post/sparsity.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa67e76b38c5ab4ee48265c427e1d67f679356713b1aab54bdabb2c980721e55
+size 65616

blocks.14.hook_resid_post/cfg.json

@@ -0,0 +1 @@
+{"d_in": 3584, "d_sae": 16384, "device": "cuda", "reshape_activations": "none", "apply_b_dec_to_input": true, "dtype": "float32", "metadata": {"sae_lens_version": "6.26.2", "sae_lens_training_version": "6.26.2", "dataset_path": "TQRG/DeltaSecommits_qwen-2.5-7b-instruct_tokenized", "hook_name": "blocks.14.hook_resid_post", "model_name": "Qwen/Qwen2.5-7B-Instruct", "model_class_name": "HookedTransformer", "hook_head_index": null, "context_size": 128, "seqpos_slice": [null, null], "model_from_pretrained_kwargs": {}, "prepend_bos": true, "exclude_special_tokens": false, "sequence_separator_token": "bos", "disable_concat_sequences": false}, "normalize_activations": "layer_norm", "architecture": "standard"}

blocks.14.hook_resid_post/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e21f3f704c516988b4c6c5b2e98cb2a35688a3cb56a180a91504faa377ecca2
+size 469842240

blocks.14.hook_resid_post/sparsity.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef9e54f4cdec3839a1a080cf3485d1a55ec5e25dfe5fb710149c5d69c6b2f04
+size 65616

blocks.27.hook_resid_post/cfg.json

@@ -0,0 +1 @@
+{"normalize_activations": "layer_norm", "reshape_activations": "none", "device": "cuda", "dtype": "float32", "apply_b_dec_to_input": true, "d_in": 3584, "metadata": {"sae_lens_version": "6.26.2", "sae_lens_training_version": "6.26.2", "dataset_path": "TQRG/DeltaSecommits_qwen-2.5-7b-instruct_tokenized", "hook_name": "blocks.27.hook_resid_post", "model_name": "Qwen/Qwen2.5-7B-Instruct", "model_class_name": "HookedTransformer", "hook_head_index": null, "context_size": 128, "seqpos_slice": [null, null], "model_from_pretrained_kwargs": {}, "prepend_bos": true, "exclude_special_tokens": false, "sequence_separator_token": "bos", "disable_concat_sequences": false}, "d_sae": 16384, "architecture": "standard"}

blocks.27.hook_resid_post/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f5620d68f3ed26184dc51e28a3656babf54fb9b31cd0238f55affe714836da
+size 469842240

blocks.27.hook_resid_post/sparsity.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c331d299a0beb5635fa87c075114fddc163c6a27bf25c8f9f8a4ada039832ec
+size 65616