SAEs detect concepts well in diffusion models but fail as direct intervention points for unlearning; a detection-guided patch replacement method yields significantly cleaner erasure results.
Transformer Circuits Thread (2023), https://transformer-circuits.pub/2023/monosemantic- features/index.html
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models
SAEs detect concepts well in diffusion models but fail as direct intervention points for unlearning; a detection-guided patch replacement method yields significantly cleaner erasure results.