AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions

Blanka Kövér, Alexandra Butoi, Anej Svete, Michael Hahn, Ryan Cotterell

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Mechanistic circuit interpretability · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train transformer on Majority instead of Paritytransformer encoder · sensitivity profile after trainingmatch to target sensitivity profileImproved
train on Parity (maximally sensitive function)transformer encoder · Parity, trainedsensitivity profileHurt
vary initialization scheme (uniform, Gaussian, Xavier uniform, Xavier Gaussian) (ablation)randomly initialized transformer · random-init sensitivity spectraskew of sensitivity spectrum toward zeroNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy