Why Does Robustness Reduce Superposition?

Title:Why Does Robustness Reduce Superposition?

Abstract:The study of adversarial examples and their origins remains an open area of research. Mechanistic interpretability, and superposition in particular, offers new avenues for approaching this problem. Gorton & Lewis (2025) demonstrate that adversarial examples arise from superposition and show empirically that adversarial training reduces superposition, yet provide no mechanistic account of why this occurs. We present an empirical explanation inspired by the feature taxonomy of Ilyas et al. (2019), tracing the following chain of causalities: adversarial training abandons non-robust features, leading to fewer total features to represent, resulting in less superposition.

9 pages, 4 figures. Accepted at the COLM 2026 Workshop on AI Interpretability (AIW)

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

arXiv:2608.22155 [cs.LG]

(or arXiv:2608.22155v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2608.22155 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.