PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
Paper
•
2602.01322
•
Published
•
8
Panagiotis Koromilas
pakoromilas
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 22 hours ago
PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
submitted
a paper
about 22 hours ago
PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
upvoted
a
paper
about 2 months ago
REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
Organizations
None yet
submitted
a
paper
to Daily Papers
about 22 hours ago
authored
a
paper
6 months ago