cs.CLJan 15, 2026

Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel

Authors: Hiroaki Yamagiwa, Yusuke Takase, Hidetoshi Shimodaira

Organizations: Kyoto University · RIKEN AIP

Abstract

Understanding relationships between attention heads is essential for interpreting the internal structure of Transformers, yet existing metrics do not capture this structure well. We focus on the subspaces spanned by attention-head weight matrices and quantify head-to-head relationships using the Projection Kernel (PK), a principal-angle-based measure of subspace similarity. Experiments on GPT2-small, BLOOM-560M, and Qwen2-0.5B-Instruct show that PK reproduces known head-to-head interactions on the IOI task more clearly than prior metrics such as the Composition Score. We further introduce a framework to quantify the informativeness of PK distributions by comparing them with a reference distribution derived from random orthogonal subspaces. As an application, we analyze a directed graph constructed from PK and show that, in GPT2-small, L4H7 acts as a hub by functioning as an Identity Head.

Figures & tables

Appendix figures & tables56 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Hierarchical Kernel Transformer: Multi-Scale Attention with an Information-Theoretic Approximation Analysis

    Apr 10, 2026Giansalvo CirrincioneAttention ApproximationTransformer Attention

  2. Projection-Free Transformers via Gaussian Kernel Attention

    May 4, 2026Debarshi Kundu, Archisman Ghosh, Swaroop Ghosh +1TransformerSelf-Attention