Revenge of Monosemanticity: Neuron Specialization as a New Form of Feature Learning in MLPs

arXiv:2608.24007 · cs.LG, stat.ML · Submitted 2026-08-25 · Read on arXiv

cs.LG, stat.ML

Submitted: 2026-08-25

Updated: 2026-09-10

Terminology

• Alignment — 10× in this paper · explained in 1 episode
• Homogeneity — 8× in this paper · explained in 2 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Adam — 6× in this paper · explained in 2 episodes
• Clustering — 6× in this paper · explained in 2 episodes
• Sample Complexity — 6× in this paper · explained in 15 episodes
• Cosine Similarity — 5× in this paper · explained in 3 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Recursive Feature Machine — 4× in this paper
• Gradient Flow — 3× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Ambient Dimension — 2× in this paper · explained in 1 episode
• Interpretability — 2× in this paper · explained in 15 episodes
• Intrinsic Dimension — 2× in this paper · explained in 2 episodes
• Mixture of Experts — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Sample Efficiency — 2× in this paper · explained in 4 episodes
• Activation Function — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Curse of Dimensionality — 1× in this paper · explained in 6 episodes
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks