Sparse Autoencoders for Scientifically Rigorous Interpretation of Vision Models
Journal:
arXiv
Published Date:
Feb 10, 2025
Abstract
To truly understand vision models, we must not only interpret their learned
features but also validate these interpretations through controlled
experiments. Current approaches either provide interpretable features without
the ability to test their causal influence, or enable model editing without
interpretable controls. We present a unified framework using sparse
autoencoders (SAEs) that bridges this gap, allowing us to discover
human-interpretable visual features and precisely manipulate them to test
hypotheses about model behavior. By applying our method to state-of-the-art
vision models, we reveal key differences in the semantic abstractions learned
by models with different pre-training objectives. We then demonstrate the
practical usage of our framework through controlled interventions across
multiple vision tasks. We show that SAEs can reliably identify and manipulate
interpretable visual features without model re-training, providing a powerful
tool for understanding and controlling vision model behavior. We provide code,
demos and models on our project website: https://osu-nlp-group.github.io/SAE-V.
