Cluster 651287

4 repos

Python · 3

Jupyter Notebook · 1

mechanistic-interpretability ·152

cross-layer-transcoder ·114

attribution-graphs ·114

visual-interface ·108

auto-interpretability ·108

transcoder ·108

transformer-circuits ·108

ai-interpretability ·108

circuit-tracing ·44

language-model ·38

Related clusters

peppinob-ol/attribution-graph-probing

Automates attribution-graph analysis via probe prompting: circuit-trace a prompt, auto-generate…

Jupyter Notebook

34 commits

TransluceAI/circuits

ADAG: Transluce's MLP neuron-level circuit tracing library

Python

2 commits

LLM-Interp/CLT-Forge

A Mechanistic Interpretability Toolkit for Cross-Layer Transcoder Training and Attribution-Graph…

Python

108

47 commits

fateme-hshm96/skel-for-circuits

Subgraph Extraction via Multi-Scale Graph Skeletonization

Python

40 commits