Release v3.7.0

.github/workflows/oracle-parity.yml

@@ -0,0 +1,57 @@
+name: Oracle Parity
+
+# Runs the @pytest.mark.slow oracle parity suite for JacobianLens.
+# Not part of the standard PR gate — requires ~4 GB VRAM and network access.
+# Triggered manually or automatically when the test file or this workflow changes.
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+      - dev*
+    paths:
+      - "tests/integration/test_jacobian_lens_oracle_parity.py"
+      - ".github/workflows/oracle-parity.yml"
+
+permissions:
+  contents: read
+
+jobs:
+  oracle-parity-checks:
+    name: Oracle Parity Checks
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          python-version: "3.12"
+          activate-environment: true
+          enable-cache: true
+
+      - name: Install dependencies
+        run: |
+          uv lock --check
+          uv sync
+
+      - name: Install oracle (pinned ORACLE_COMMIT from test file)
+        run: |
+          ORACLE_COMMIT=$(python -c "
+          import re, pathlib
+          src = pathlib.Path('tests/integration/test_jacobian_lens_oracle_parity.py').read_text()
+          print(re.search(r'ORACLE_COMMIT = \"([^\"]+)\"', src).group(1))
+          ")
+          uv pip install "git+https://github.com/anthropics/jacobian-lens.git@${ORACLE_COMMIT}"
+
+      - name: Authenticate HuggingFace
+        if: env.HF_TOKEN != ''
+        run: uv run python -c "import os; from huggingface_hub import login; login(token=os.environ['HF_TOKEN'])"
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+
+      - name: Oracle Parity Test
+        run: uv run pytest tests/integration/test_jacobian_lens_oracle_parity.py -v -m slow
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}

README.md

@@ -20,7 +20,7 @@ interpretability](https://distill.pub/2020/circuits/zoom-in/) of GPT-2 Style lan
 goal of mechanistic interpretability is to take a trained model and reverse engineer the algorithms
 the model learned during training from its weights.
 
-TransformerLens lets you load in 9,000+ open source language models across 50+ architecture families,
+TransformerLens lets you load in 15,000+ open source language models across 140+ architecture families,
 and exposes the internal activations of the model to you. You can cache any internal activation in the
 model, and add in functions to edit, remove or replace these activations as the model runs.
 
@@ -52,7 +52,7 @@ logits, activations = bridge.run_with_cache("Hello World")
 
 > Gated models (Llama, Mistral, Gemma, ...) require `HF_TOKEN` in your environment. See [Environment Variables](https://TransformerLensOrg.github.io/TransformerLens/content/getting_started.html#environment-variables) for the full list.
 
-`TransformerBridge` is the recommended 3.0 path and supports 9,000+ models across 50+ architecture families (see [`supported_models.json`](transformer_lens/tools/model_registry/data/supported_models.json) for the full inventory). By default it preserves raw HuggingFace weights – logits and activations match HF, *not* legacy `HookedTransformer` (which folds LayerNorm and centers weights by default). Call `bridge.enable_compatibility_mode()` after booting for HookedTransformer-equivalent numerics. The legacy `HookedTransformer.from_pretrained` API is still available but deprecated — see the [Migrating to TransformerLens 3](https://TransformerLensOrg.github.io/TransformerLens/content/migrating_to_v3.html) guide.
+`TransformerBridge` is the recommended path and supports 15,000+ models across 140+ architecture families (see [`supported_models.json`](transformer_lens/tools/model_registry/data/supported_models.json) for the full inventory). By default it preserves raw HuggingFace weights – logits and activations match HF, *not* legacy `HookedTransformer` (which folds LayerNorm and centers weights by default). Call `bridge.enable_compatibility_mode()` after booting for HookedTransformer-equivalent numerics. The legacy `HookedTransformer.from_pretrained` API is still available but deprecated — see the [Migrating to TransformerLens 3](https://TransformerLensOrg.github.io/TransformerLens/content/migrating_to_v3.html) guide.
 
 ## Key Tutorials
 

demos/Grokking_Demo.ipynb

@@ -385,7 +385,18 @@
    "cell_type": "code",
    "execution_count": 15,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "DeprecationWarning:\n",
+      "\n",
+      "HookedTransformer is deprecated and will be removed in 4.0. Use TransformerBridge.boot_transformers(...) instead, then call enable_compatibility_mode() for HookedTransformer-equivalent numerics.\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "model = HookedTransformer(cfg)"
    ]

demos/No_Position_Experiment.ipynb

@@ -144,7 +144,18 @@
    "cell_type": "code",
    "execution_count": 35,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "DeprecationWarning:\n",
+      "\n",
+      "HookedTransformer is deprecated and will be removed in 4.0. Use TransformerBridge.boot_transformers(...) instead, then call enable_compatibility_mode() for HookedTransformer-equivalent numerics.\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "cfg = HookedTransformerConfig(\n",
     "    n_layers=2,\n",

demos/Othello_GPT.ipynb

@@ -279,7 +279,18 @@
    "cell_type": "code",
    "execution_count": 56,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "DeprecationWarning:\n",
+      "\n",
+      "HookedTransformer is deprecated and will be removed in 4.0. Use TransformerBridge.boot_transformers(...) instead, then call enable_compatibility_mode() for HookedTransformer-equivalent numerics.\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "import transformer_lens.utilities as utils\n",
     "\n",

demos/doc_sanitize.cfg

@@ -33,3 +33,7 @@ replace: \1
 [regex6d]
 regex: (0\.[1-9]\d{2})\d+
 replace: \1
+
+[regex7]
+regex: [^\n]*DeprecationWarning:(?=\n\nHookedTransformer is deprecated and will be removed in 4\.0\. Use TransformerBridge\.boot_transformers\(\.\.\.\) instead, then call enable_compatibility_mode\(\) for HookedTransformer-equivalent numerics\.)
+replace: DeprecationWarning: