Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
Keywords: Developmental Interpretability, Mechanistic Interpretability, Singular Learning Theory, Learning Dynamics, Stagewise development, Model complexity
TL;DR: The paper studies how language model attention heads develop during training using new, refined variants of the Local Learning Coefficient (LLC)
Abstract: We introduce refined variants of the Local Learning Coefficient (LLC), a measure of model complexity grounded in singular learning theory, to study the development of internal structure in transformer language models during training. By applying these refined LLCs (rLLCs) to individual components of a two-layer attention-only transformer, we gain novel insights into the progressive differentiation and specialization of attention heads. Our methodology reveals how attention heads differentiate into distinct functional roles over the course of training, analyzes the types of data these heads specialize to process, and discovers a previously unidentified multigram circuit. These findings demonstrate that rLLCs provide a principled, quantitative toolkit for developmental interpretability, which aims to understand models through their evolution across the learning process. This work advances the field of developmental interpretability by providing a mathematically rigorous approach to understanding neural networks through the lens of their learning process. More broadly, this work takes a step towards establishing the correspondence between data distributional structure, geometric properties of the loss landscape, learning dynamics, and emergent computational structures in neural networks.
Primary Area: interpretability and explainable AI
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 9016
Loading