arXiv Machine Learning
Certified Mechanistic Interpretability: Lifting Single-Input Findings to Bounded Neighbourhoods
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jul 30
Towards Verifiable Transformers: Solver-Checkable Circuit Explanations
arXiv:2605. 24033v2 Announce Type: replace Abstract: Mechanistic interpretability typically discovers circuits and then argues what they do from examples and ablations.
arXiv AI
Jun 30
Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers
arXiv:2510. 25013v2 Announce Type: replace-cross Abstract: Mechanistic interpretability aims to reverse-engineer large language models (LLMs) into human-understandable computational circuits.
arXiv Machine Learning
Jul 9
Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning
arXiv:2607. 07316v1 Announce Type: new Abstract: This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms of modern neural networks.
arXiv Machine Learning
Jul 2
Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
arXiv:2607. 00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact.
arXiv Machine Learning
Jun 19
Influence-Guided Concolic Testing of Transformer Robustness
arXiv:2509. 23806v2 Announce Type: replace-cross Abstract: Concolic testing for neural networks alternates concrete execution with constraint solving to search for inputs that flip model decisions.
arXiv Machine Learning
Sep 1
Universal Transformers for Circuit Computations: Perfect Length Generalization in Tiny Transformers
arXiv:2608.31067v1 Announce Type: new Abstract: Learning generalizable algorithmic computations remains a challenge for neural networks, as reflected in persistent failures on compositional and lengt...