Transcoders Find Interpretable LLM Feature Circuits
Paper
•
2406.11944
•
Published
•
2
Arthur Conmy (GDM Account)
ArthurConmyGDM
AI & ML interests
Interpretability, AI Safety, AI Alignment
Recent Activity
new activity
about 7 hours ago
google/gemma-scope-9b-pt-res:Removing SAEs with LR != 7e-5
new activity
29 days ago
google/gemma-scope-9b-pt-res:Layer 13 saes raising "zipfile.BadZipFile: File is not a zip file"
liked
a model
about 2 months ago
google/gemma-scope
Organizations
