You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A Library for Mechanistic Interpretability of Generative Language Models. Maintained by [Bryce Meyer](https://github.com/bryce13950) and created by [Neel Nanda](https://neelnanda.io/about)
13
+
A Library for Mechanistic Interpretability of Generative Language Models. Maintained by [Bryce Meyer](https://github.com/bryce13950) and [Jonah Larson](https://github.com/jlarson4); created by [Neel Nanda](https://neelnanda.io/about)
> 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.
54
+
53
55
`TransformerBridge` is the recommended 3.0 path and supports 50+ architectures. 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.
0 commit comments