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

Apr 10, 2026

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

The Hierarchical Kernel Transformer (HKT) is a multi-scale attention mechanism that processes sequences at L resolution levels via trainable causal downsampling, combining level-specific score matrices through learned convex weights. The total computational cost is bounded by 4/3 times that of standard attention, reaching 1.3125x for L = 3. Four theoretical results are established. (i) The hierarchical score matrix defines a positive semidefinite kernel under a sufficient condition on the symmetrised bilinear form (Proposition 3.1). (ii) The asymmetric score matrix decomposes uniquely into a symmetric part controlling reciprocal attention and an antisymmetric part controlling directional attention; HKT provides L independent such pairs across scales, one per resolution level (Propositions 3.5-3.6). (iii) The approximation error decomposes into three interpretable components with an explicit non-Gaussian correction and a geometric decay bound in L (Theorem 4.3, Proposition 4.4). (iv) HKT strictly subsumes single-head standard attention and causal convolution (Proposition 3.4). Experiments over 3 random seeds show consistent gains over retrained standard attention baselines: +4.77pp on synthetic ListOps (55.10+-0.29% vs 50.33+-0.12%, T = 512), +1.44pp on sequential CIFAR-10 (35.45+-0.09% vs 34.01+-0.19%, T = 1,024), and +7.47pp on IMDB character-level sentiment (70.19+-0.57% vs 62.72+-0.40%, T = 1,024), all at 1.31x overhead.
Nov 9, 2026

A Geometric Invariant of Attention Predicts Head Specialization from Weights Alone

Transformers are built with continuous symmetries in the attention mechanism. We derive ρρ, a scalar invariant that measures each head's capacity to couple to rotary positional encodings. This framework allows us to analyze heads without forward passes, opening a new research direction into data-independent analysis of modern LLMs. Empirically, we find that ρρ predicts induction heads, the most-studied circuit type in mechanistic interpretability, with Spearman correlation between −0.55-0.55 and −0.74-0.74 across four bias-free RoPE models spanning 135135M to 77B parameters. As a preliminary proof of concept, we use ρρ to apply YaRN to only the top-50% positional heads, which degrades perplexity less than uniform application. Code is available at https://github.com/MPedraBento/rho-invariant.
May 4, 2026

Projection-Free Transformers via Gaussian Kernel Attention

Self-attention in Transformers is typically implemented as softmax(QK⊤/d)V\mathrm{softmax}(QK^\top/\sqrt{d})V, where Q=XWQQ=XW_Q, K=XWKK=XW_K, and V=XWVV=XW_V are learned linear projections of the input XX. We ask whether these learned projections are necessary, or whether they can be replaced by a simpler similarity-based diffusion operator. We introduce Gaussian Kernel Attention (GKA), a drop-in replacement for dot-product attention that computes token affinities directly using a Gaussian radial basis function (RBF) kernel applied to per-head token features. Each head learns only a bandwidth parameter σhσ_h, while a single output projection WOW_O preserves compatibility with the standard Transformer interface. GKA can be interpreted as normalized kernel regression over tokens, linking modern Transformer architectures to classical non-local filtering and kernel smoothing methods. We evaluate GKA in both vision and language modeling settings. For autoregressive language modeling within the nanochat framework, we implement causal masking and sliding-window constraints by masking and renormalizing the Gaussian kernel. At depth 20, a GKA model with 0.42×0.42\times the parameters and 0.49×0.49\times the total training FLOPs of a standard attention baseline trains stably, exhibits a near-zero train-validation gap, and demonstrates competitive behavior on standard benchmarks, albeit with higher bits-per-byte (BPB) at this compute scale. Overall, GKA provides a minimal, interpretable attention mechanism with an explicit locality scale, offering a dimension in the accuracy-efficiency trade-off for Transformer design.