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

Tuned Lens

Creator
Creator
Seonglae Cho
Created
Created
2024 Oct 14 1:26
Editor
Editor
Seonglae Cho
Edited
Edited
2025 Feb 1 21:50
Refs
Refs
tuned-lens
AlignmentResearch • Updated 2025 Jan 30 18:58
 
 
 
 
 
 
Tuned Lens
Tools for understanding how transformer predictions are built layer-by-layer.
https://tuned-lens.readthedocs.io/en/latest/
 
 

Backlinks

Patchscopes

Recommendations

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