Tag
This post explores DINOv3 vision embeddings by generating images that correspond to specific embedding directions, using gradient optimization and augmentation strategies to invert the model.
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.
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.