Mechanistic Interpretability of Diffusion Models: Circuit-Level Analysis and Causal Validation

ArXi:2506.17237v2 Announce Type: replace We present a quantitative circuit-level analysis of diffusion models, establishing computational pathways and mechanistic principles underlying image generation processes. Through systematic intervention experiments across 2,000 synthetic and 2,000 CelebA facial images, we discover fundamental algorithmic differences in how diffusion architectures process synthetic versus naturalistic data distributions.