Why Does Robustness Reduce Superposition?

The paper investigates why robustness training reduces superposition in neural networks. It builds on prior work showing that adversarial examples stem from superposition and that adversarial training diminishes it, but offers no mechanistic explanation. The authors provide an empirical account linking the abandonment of non‑robust features during adversarial training to a reduced number of features overall, thereby lowering superposition.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• safety