Revenge of Monosemanticity: Neuron Specialization as a New Form of Feature Learning in MLPs
cs.LG, stat.ML
Submitted: 2026-08-25
Updated: 2026-10-27
License: http://creativecommons.org/licenses/by/4.0/
The gist: Understanding how neural networks learn and organize features is central to understanding their behavior.
Terminology
Abstract
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 to specialize gives MLPs a provable data-efficiency advantage over feature-learning methods based on a global low-dimensional representation.
Sources
- The Generative Leap: Sharp Sample Complexity for Efficiently Learning Gaussian Multi-Index Models
- Grokking modular arithmetic
- On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking
- Gaussian Error Linear Units (GELUs)
- Progress measures for grokking via mechanistic interpretability
- GLU Variants Improve Transformer
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks