Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective
Abstract: To better interpret the intrinsic mechanism of large language models (LLMs), recent studies focus on monosemanticity on its basic units. A monosemantic neuron is dedicated to a single and specific concept, which forms a one-to-one correlation between neurons and concepts. Despite extensive research in monosemanticity probing, it remains unclear whether monosemanticity is beneficial or harmful to model capacity. To explore this question, we revisit monosemanticity from the feature decorrelation perspective and advocate for its encouragement. We experimentally observe that the current conclusion by \citet{wang2024learning}, which suggests that decreasing monosemanticity enhances model performance, does not hold when the model changes. Instead, we demonstrate that monosemanticity consistently exhibits a positive correlation with model capacity, in the preference alignment process.
Consequently, we apply feature correlation as a proxy for monosemanticity and incorporate a feature decorrelation regularizer into the dynamic preference optimization process. The experiments show that our method not only enhances representation diversity and activation sparsity but also improves preference alignment performance.
Paper Type: Long
Research Area: Interpretability and Analysis of Models for NLP
Research Area Keywords: Large Language Model, Mechanistic Interpretability, Monosemanticity, Preference Optimisation
Contribution Types: Model analysis & interpretability
Languages Studied: English
Submission Number: 3397
Loading