Markovian Circuit Tracing: Ground-Truth Tests of Transformer State Abstractions

arXiv:2605.20824 · cs.LG · Submitted 2026-05-20 · Read on arXiv

cs.LG

Submitted: 2026-05-20

Updated: 2026-10-26

Terminology

• Transformer — 4× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Markovian Circuit Tracing — 2× in this paper
• Evaluation Framework — 1× in this paper · explained in 3 episodes
• Hidden Markov Model — 1× in this paper
• Interpretability — 1× in this paper · explained in 15 episodes
• Transformers — 1× in this paper · explained in 2 episodes

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