preprint Open access

Microscopic Pe: Measuring Péclet Flow on Circuit Attribution Graphs

  • Zenodo (CERN European Organization for Nuclear Research)
  • European Organization for Nuclear Research
Research footprint

At a glance

Citations
0
References
0
Comments
0
Paper overview

Abstract

Anthropic's circuit tracing (2025) — attribution graphs revealing computational paths through language models — provides the microscope for measuring Péclet number at the feature level. We define Pe on attribution graph edges as the ratio of directed information flow (drift) to undirected spreading (diffusion) through cross-layer transcoder features. Jailbreak circuits should exhibit measurable Pe gradients: Pe increases along the computational path. The 12 jailbreak patterns detected by the Void Framework's Twilight monitoring should correspond to specific high-Pe subgraphs. This connects macroscopic Pe scoring (N=1,344 platforms) to microscopic mechanism, bridging mechanistic interpretability and thermodynamic field theory.

Record transparency

Publication details

DOI
10.5281/zenodo.19261142
OpenAlex
W7141325159
Document type
preprint
Language
EN
Source
Zenodo (CERN European Organization for Nuclear Research)
Last metadata update
Community

Comments

Log in to join the discussion.

  1. No comments yet. Start the discussion.