Intermediate transformer states sit far from the output axis on purpose: that position insulates attention's cross-token mixing, and the frame can be prescribed in advance without loss.
An Analysis of Residual-Stream Geometry Across Transformer Depth
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We propose a transition-centred geometric analysis of transformer residual streams. Relative displacement measures how \emph{far} representations move between consecutive layers, and orthogonal Procrustes analysis separates each transition into a rigid rotation and a non-rigid residual. Across six instruction-tuned models, on code generation and cross-lingual translation, these measurements reveal reproducible depth regularities. Relative displacement is strongly layer-dependent; typically larger early and late, with a quieter middle third; and nearly invariant across conditions within each model. Rotation magnitude is nearly constant across depth, while Procrustes residual and angle concentration remain depth-modulated, with residual peaking at the final transition. During generation, non-English targets show larger final-layer displacement and residual than English targets. We present these as descriptive geometric regularities, not as measures of computational effort or causal explanations. The contribution is a measurement framework for residual-stream transitions and evidence that, in the settings studied here, depth curves are model-dependent and largely condition-stable.
citation-role summary
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Off-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does So
Intermediate transformer states sit far from the output axis on purpose: that position insulates attention's cross-token mixing, and the frame can be prescribed in advance without loss.