Revenge of Monosemanticity: Neuron Specialization as a New Form of Feature Learning in MLPs
Understanding how neural networks learn and organize features is central to understanding their behavior. Much existing theory of feature learning has focused on the emergence of a global low-dimensional representation. We show that this picture is incomplete. In regression problems with clustered data, we demonstrate that multilayer perceptrons (MLPs) naturally develop monosemantic specialized neurons: individual neurons become strongly aligned with a specific predictive feature relevant to a particular region of the input space. Rather than learning a single global low-dimensional representation, MLPs learn a collection of local low-dimensional representations. We show that this ability...
| Authors | Amirhesam Abedsoltan, Enric Boix-Adsera, Fivos Kalogiannis et al. |
|---|---|
| Primary category | cs.LG |
| Published | 25 August 2026 |
| Last updated at source | 10 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.