Publications
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
We show that Sparse Autoencoders (SAEs), despite their promise for interpretability, are highly unstable. We introduced two new benchmarks to assess SAW dictionary quality, and propose Archetypal SAEs (A-SAEs), which constrain dictionary atoms to the data’s convex hull, greatly improving stability. Our relaxed version, RA-SAE, matches top reconstruction performance and consistently learns more structured, meaningful representations.
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
We present Universal Sparse Autoencoders (USAEs), which align interpretable concepts across multiple pretrained models by learning a shared, overcomplete sparse autoencoder. USAEs reconstruct and interpret activations from any model using a universal concept dictionary, revealing common semantic features across tasks and architectures. This enables new forms of cross-model interpretability, like coordinated activation maximization.