Thomas Fel

Publications

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

Interpretability

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.

February 17, 2025
Date Range

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment

Interpretability

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.

February 5, 2025
Date Range

News

No items found.

Research

Our research explores a portfolio of high-potential agendas.

Events

Our events bring together global leaders in AI.

Programs

Our programs build the field of trustworthy and secure AI