arXiv (All)
open access
When Do Attention-Head Ablations Support Causal Claims? Projection-Level Confounds, Floor Effects, and Matched Controls
Attention-head ablation, zeroing a head and measuring the resulting change in task performance, is a common method for inferring which components of a language model are causally responsible for a behavior. We show using GPT-2 small that this inference can be fragile unless the intervention semantic
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- MechaTerp-TRACE: A Novel Approach for Component Ablation Analysis in Language Models#1036846
- Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations#1156399
- Same Evidence, Different Target: Decoding How Diagnostic Evidence Bears on Causal Questions from Language-Model States#411055
- Language Models Can Control Their Own Attention#632836
- MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation#1143319
Record · ID 1155308
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive