PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
Paper
• 2602.01322 • Published
• 8
Theodoros Giannakopoulos
tyiannak
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding upvoted a paper 3 months ago
REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion Organizations
upvoted a paper about 1 month ago