Skip to content
conftrace_
2025 ICML ICML 2025

Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Thomas FEL, Ekdeep Singh Lubana, Jacob S. Prince, Matthew Kowal, Victor Boutin, Isabel Papadimitriou, Binxu Wang, Martin Wattenberg, Demba E. Ba, Talia Konkle

Topics

Artificial Intelligence > Core AI > Interpretability Machine Learning > Core Methods > Representation Learning Deep Learning > Architectures > Neural Networks

Keywords

dictionary learning identifiability stability convex hull archetypal saes plausibility
Download PDF