Scalable Circuit Learning for Interpreting Large Language Models

arXiv:2606.16939 · cs.LG, cs.AI · Submitted 2026-06-15 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-06-15

Updated: 2026-10-09

Terminology

• Interpretability — 2× in this paper · explained in 15 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Mechanistic interpretability — 1× in this paper · explained in 2 episodes

Sources

• BatchTopK Sparse Autoencoders
• Sparse Autoencoders Find Highly Interpretable Features in Language Models
• Toy Models of Superposition
• Finding Neurons in a Haystack: Case Studies with Sparse Probing
• Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
• RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching
• AtP*: An efficient and scalable method for localizing LLM behaviour to components
• In-context Learning and Induction Heads
• Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
• Gemma 2: Improving Open Language Models at a Practical Size
• Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias
• Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models
• Representation Engineering: A Top-Down Approach to AI Transparency

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks