Sparse autoencoders and ITDA produce comparably interpretable and steerable features in FLUX.1, outperforming MLP neurons on an automated visual interpretability metric.
Activation atlas
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning
Sparse autoencoders and ITDA produce comparably interpretable and steerable features in FLUX.1, outperforming MLP neurons on an automated visual interpretability metric.