feature-visualization

Tag

Cards List
#feature-visualization

Deep Dreams Are Made of This: Visualizing Monosemantic Features in Diffusion Models

arXiv cs.LG · yesterday Cached

This paper introduces Latent Visualization by Optimization (LVO), a mechanistic interpretability technique that uses sparse autoencoders to visualize monosemantic features in diffusion models like Stable Diffusion 1.5.

0 favorites 0 likes
#feature-visualization

Introducing Activation Atlases

OpenAI Blog · 2019-03-06 Cached

OpenAI introduces Activation Atlases, a technique for visualizing and understanding the internal representations of neural networks, enabling humans to discover spurious correlations and unexpected behaviors such as fooling image classifiers by adding noodles to images.

0 favorites 0 likes
← Back to home

Submit Feedback