AINeutralarXiv – CS AI · 3h ago6/10
🧠
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
Researchers introduce residualized temporal sparse autoencoders (SAEs) to interpret how text-to-image diffusion models generate images over time. By analyzing activation trajectories across the denoising process rather than static snapshots, the method captures interpretable features that go beyond simple linear predictability, enabling better understanding of model internals.
🧠 Stable Diffusion