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

Jan 1, 2025·

Thomas Fel

,

Ekdeep Singh Lubana

,

Jacob S Prince

,

Matthew Kowal

,

Victor Boutin

,

Isabel Papadimitriou

Binxu Wang

,

Martin Wattenberg

,

Demba Ba

,

Talia Konkle

· 0 min read

PDF Cite Code

Interpretability Computer Vision

Authors

Binxu Wang

Research Fellow

---

← An analytical theory of power law spectral bias in the learning dynamics of diffusion models Mar 1, 2025

The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its Applications Dec 1, 2024 →