How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution

2026-08-27

AI Summary

本文通过引入概念定向归因(CTA)方法，解决了线性探针如何产生内部概念表示的问题，并解释了影响探针性能的内部计算机制。

Abstract

Transcoder attribution graphs are usually trained to explain why a model assigns high probability to a particular next token. We introduce Concept-Targeted Attribution (CTA), which instead trains attribution graphs with respect to a linear probe direction. CTA therefore yields probe-specific circuits that explain why an internal concept representation arises in a prompt, independently of whether it is expressed in the generated token. Using Cross-Layer Transcoders, we show that these probe-targeted graphs contain predictive structure: graph-level features predict probe accuracy across four widely studied concept categories ($ρ= 0.91$, $R^2 = 0.84$), while local features identify the sparse components driving per-prompt classification. This connects probe performance to interpretable circuit structure, allowing us to ask not only whether a probe works, but which internal computations make it work. Causal ablations further show that probe-targeted and logit-targeted graphs capture functionally distinct mechanisms. Removing probe-relevant features reduces internal concept scores while largely preserving generated tokens, whereas removing logit-relevant features changes the generated token in 92% to 100% of cases with near-zero effect on probe scores. CTA provides a framework for moving from behavioral probe accuracy to mechanistic explanations of probe performance, enabling more detailed audits of internal concept representations, including safety-critical ones. Our code is available at https://github.com/vedantpalit/concept-targeted-attribution

Problem

• Linear Probes
• Concept-Targeted Attribution
• Internal Concept Representation
• Mechanistic Explanations

Innovation

• Concept-Targeted Attribution (CTA)
• Cross-Layer Transcoders
• probe-specific circuits