Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/Mechanistic interpretability/Activation Engineering/Transformer Lens/
Transformer Lens Patching
Search

Transformer Lens Patching

Creator
Creator
Seonglae Cho
Created
Created
2025 Mar 6 22:29
Editor
Editor
Seonglae Cho
Edited
Edited
2025 Mar 6 22:29
Refs
Refs
Activation Patching
 
 
 
 
 
 
transformer_lens.patching - TransformerLens Documentation
A module for patching activations in a transformer model, and measuring the effect of the patch on the output. This implements the activation patching technique for a range of types of activation. The structure is to have a single generic_activation_patch() function that does everything, and to have a range of specialised functions for specific types of activation.
transformer_lens.patching - TransformerLens Documentation
https://transformerlensorg.github.io/TransformerLens/generated/code/transformer_lens.patching.html#transformer_lens.patching.get_act_patch_resid_mid
 
 

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/Mechanistic interpretability/Activation Engineering/Transformer Lens/
Transformer Lens Patching
Copyright Seonglae Cho