Upload folder using huggingface_hub

README.md

@@ -0,0 +1,51 @@
+---
+license: mit
+library_name: transformers
+tags:
+  - gpt2
+  - onnx
+  - mechanistic-interpretability
+  - circuit-ablation
+  - rti-circuit
+base_model: openai-community/gpt2
+---
+
+# GPT-2 with RTI Circuit Zero-Ablated
+
+GPT-2 (124M) with the 15-head **Repeated Token Identification (RTI) circuit** removed via zero ablation.
+
+## What was ablated
+
+The RTI circuit consists of 15 attention heads across 4 functional tiers:
+
+| Tier | Heads | Function |
+|------|-------|----------|
+| Backbone | 0.8, 0.9, 0.11 | Broad token matching via positional/frequency features |
+| Detector | 4.11 | Repeated-token detection gate |
+| Copier | 4.0, 5.6, 5.7, 7.0, 8.4, 8.7, 9.3, 9.10 | Copy repeated token identity to output |
+| Readout | 10.11, 11.9, 11.11 | Route copied information to final logits |
+
+## Ablation method
+
+**Zero ablation**: For each circuit head, the corresponding columns of `c_proj.weight` (the output projection W_O) were set to zero. This prevents the head from writing anything to the residual stream, effectively removing its contribution.
+
+## Effect
+
+The ablated model loses the ability to predict repeated tokens. For example:
+- **Normal GPT-2**: "The cat sat on the mat. The cat" → " was a little bit older than me, but I"
+- **Zero-ablated**: "The cat sat on the mat. The cat" → " sat on the mat. The cat sat on the"
+
+## Usage with Transformers.js
+
+```javascript
+import { AutoModelForCausalLM, AutoTokenizer } from '@huggingface/transformers';
+
+const model = await AutoModelForCausalLM.from_pretrained('elliottower2/gpt2-rti-zero-ablated', {
+  dtype: 'fp32',
+});
+const tokenizer = await AutoTokenizer.from_pretrained('elliottower2/gpt2-rti-zero-ablated');
+```
+
+## Citation
+
+Part of the factorization-circuits project studying weight-space circuit discovery in transformers.

config.json

@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.39.3"
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ca95622cb4a8566fbbaefa0e7ecd9c250e8ab39b0728bd241aa634e962a8af
+size 653663501

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}