$\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models

Understand

We study $\textit{how}$ rich visual semantic information is represented within various layers and denoising timesteps of different diffusion architectures.

• We uncover monosemantic interpretable features by leveraging k-sparse autoencoders (k-SAE).
• We substantiate our mechanistic interpretations via transfer learning using light-weight classifiers on off-the-shelf diffusion models' features.
• On $4$ datasets, we demonstrate the effectiveness of diffusion features for representation learning.