When Do Attention-Head Ablations Support Causal Claims? Projection-Level Confounds, Floor Effects, and Matched Controls

arXiv:2610.00373 · cs.LG, cs.CL · Submitted 2026-09-30 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/TheClassicTechno/InterpretabilityNLPProject

Terminology

• Ablation — 22× in this paper · explained in 1 episode
• Accuracy — 15× in this paper · explained in 1 episode
• Transformer — 6× in this paper · explained in 2 episodes
• Interpretability — 3× in this paper · explained in 15 episodes
• Provenance — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Activation Patching — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• In-context Learning and Induction Heads

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks