Research map / Label-efficient and robust learning / Recognition and long-tail
Decomposing Query-Key Feature Interactions Using Contrastive Covariances
Andrew Lee, Yonatan Belinkov, Fernanda Viégas, Martin Wattenberg
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 changed | Where | Measured | Effect |
|---|---|---|---|
| intervene on both recovered latent subspaces z1 and z2 instead of random subspaces of the same dimension (ablation) | contrastive covariance QK decomposition on toy attention head · Payload retrieval toy task | attention shifted from original to target token | Improved |
| intervene on the recovered 5-dimensional categorical subspace instead of a random 5-dimensional subspace (ablation) | Filter Heads in Llama 3.1-8B Instruct · Categorical Filter Heads | attention shift to target token | Improved |
| intervene on both order-ID and lexical subspaces instead of only one (ablation) | binding heads in Llama 3.1-8B Instruct · Binding task | attention shift to target box | Improved |
| intervene on random subspaces of the same ranks as order-ID and lexical subspaces (ablation) | binding heads in Llama 3.1-8B Instruct · Binding task | attention shift to target box | No clear effect |
| reduce head dimension so that r1 + r2 exceeds d_head (ablation) | contrastive covariance rank recovery · Payload retrieval toy task | rank recovery | Hurt |
Closest papers by meaning
- Listening to the Wise Few: Query–Key Alignment Unlocks Latent Correct Answers in Large Language Models (NeurIPS 2026 · similarity 0.87)
- Dissecting Query-Key Interaction in Vision Transformers (NeurIPS 2024 · similarity 0.85)
- Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding (ICML 2025 · similarity 0.85)
- Correlation and Navigation in the Vocabulary Key Representation Space of Language Models (ICLR 2025 · similarity 0.85)
- Don't Lose Focus: Activation Steering via Key-Orthogonal Projections (NeurIPS 2026 · similarity 0.84)
- Selective Attention: Enhancing Transformer through Principled Context Control (NeurIPS 2024 · similarity 0.84)
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.
