Circuit

Circuit discovery methods localize the minimal subgraph of a transformer's computational graph (a set of nodes such as attention heads and MLPs, together with the edges that connect them) that is causally responsible for a specific model behavior. Rather than scoring individual objects in isolation, these techniques recover an end-to-end mechanism by jointly identifying which components, and which information pathways between them, must be preserved to reproduce the behavior on a task distribution.

zjunlp Updated 1.5k repo stars

File contents

zjunlp/mechanist commit 457d850c71

Frequently asked questions

npx get-skill add zjunlp/circuit