AI RESEARCH
Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP
arXiv CS.CV
•
ArXi:2604.05724v1 Announce Type: new Sparse Autoencoders (SAEs) have emerged as a powerful tool for interpreting the internal representations of CLIP vision encoders, yet existing analyses largely focus on the semantic meaning of individual features. We