Disentangling Representation Evolution in Transformers through Directional Decomposition
Decomposes transformer representation updates into parallel and perpendicular components, linking geometry to editing robustness and better pretraining.
The paper decomposes learned transformer updates into parallel and perpendicular components relative to the hidden state, finding substantial parallel components beyond the residual identity path across pretrained models. Targeted edits reveal exclude-self value-space parallel manipulation is more robust than residual-space or perpendicular alternatives, and perpendicular error separates compression methods more clearly. Applying full-aggregate parallel suppression during from-scratch pretraining lowers validation loss and improves downstream averages, with the value-space variant strongest. Code is released on GitHub.
- Decomposes representation updates into parallel and perpendicular components
- Value-space exclude-self edits markedly more robust than alternatives
- Perpendicular error cleanly separates compression methods
- Parallel suppression during pretraining lowers validation loss; code released
From the original article
1 min read at arxiv.orgTransformer representations evolve through learned additive transformations that either preserve their current direction or redirect it. We study this evolution as a functional geometry, decomposing learned updates into parallel and perpendicular components. Across pretrained models, we find substantial parallel components beyond the residual identity path.
By Shwai He · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.