Direct Path Patching

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2024 Oct 14 1:11
Editor
Edited
Edited
2025 Feb 1 22:9
Refs
Refs
Model as a
Computational Graph
, Formally, we break down the residual stream as input to component 2 into the sum of the output of each previous component. We subtract off the corrupted value of component 1’s output and patch in the clean value of component 1’s output.
 
 
 
 
 
 
A Comprehensive Mechanistic Interpretability Explainer & Glossary - Dynalist
Dynalist lets you organize your ideas and tasks in simple lists. It's powerful, yet easy to use. Try the live demo now, no need to sign up.
 
 
 

Recommendations