SOURCE-LINKED INTELLIGENCE

Interpretability for Turing Machines

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

We show that susceptibilities, an interpretability technique developed for neural networks, can identify the presence of algorithmic structure in Turing machines by probing the local loss landscape of a learning problem for noisy Turing machines introduced by Murfet and Troiani (arXiv:2504.08075). We prove that symmetries and path separation in the algorithm implemented by a Turing machine induce permutation symmetries and low-rank blocks in its susceptibility matrix. We study this empirically on a set of deterministic finite automata (DFAs) and demonstrate that algorithmic features can be rec

Read original source ↗ Open in workspace

recordType

paper

region

Global