Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders

This paper introduces new sparsity regularizers for Top-k sparse autoencoders to improve the interpretability of features in vision foundation models.

Firefly links to the original publisher. The summary above is AI-generated for orientation and may differ from the source. The “current rank score” decays over time so newer significant stories surface first.