ImageNetette

anchor

Findings

• IC-446In Stable Diffusion v1.5, concept-generating neurons are localized in the second layer of FFNs, spanning less than 3% of FFN parameters, and are disentangled from object-generating neurons [eval]
• IC-447CLIP ViT-B/16 produces noisy saliency maps and contains only 42 concept detectors, indicating poor visual interpretability [eval]
• IC-450LLaVA with the original CLIP encoder produces noisy, non-sparse attention maps that poorly localize to the objects described in generated text [eval]