2 papers
cs.LG2025
The Deleuzian Representation Hypothesis
Clément Cornet, Romaric Besançon, Hervé Le Borgne
We propose an alternative to sparse autoencoders (SAEs) as a simple and effective unsupervised method for extracting interpretable concepts from neural networks. The core idea is t…
cs.CV2025
Explaining How Visual, Textual and Multimodal Encoders Share Concepts
Clément Cornet, Romaric Besançon, Hervé Le Borgne
Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different mode…