Transcoders Find Interpretable LLM Feature Circuits
Paper
•
2406.11944
•
Published
•
2
Arthur Conmy (GDM Account)
ArthurConmyGDM
21world's profile picture
hanspeterlyngsoeraaschoujensen's profile picture
sboughorbel's profile picture
·
AI & ML interests
Interpretability, AI Safety, AI Alignment
Recent Activity
liked
a model
20 days ago
google/gemma-scope
liked
a model
23 days ago
fnlp/Llama-Scope
New activity
30 days ago
google/gemma-scope:suggestion: notate the canonical SAEs
Organizations
