Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
Paper
•
2502.12892
•
Published
•
2
Binxu Wang
binxu
AI & ML interests
Generative modelling and optimization in application to neuroscience
Recent Activity
upvoted
a
paper
17 days ago
Linear representations in language models can change dramatically over a conversation
Organizations
None yet
authored
3
papers
9 months ago