SharedSAE: a unified sparse dictionary across u-net blocks and denoising time for diffusion models
arXiv:2610.13997v1 Announce Type: new Abstract: Concept representations in diffusion models drift across network depth and denoising time, yet existing sparse autoencoders offer only per-block or per-timestep dictionaries, leaving no single feature dictionary for localization and intervention in th…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-14 04:00 · arXiv cs.CV
SharedSAE: a unified sparse dictionary across u-net blocks and denoising time for diffusion models