cs.LGNov 16, 2026

Pretty Linear Liars: Unregularized Probes Favor Intervention-Unfaithful Features

Authors: Karl Vilhelmsson Emneby, Julian Yocum, Cameron Allen

Organizations: Center for Human-Compatible AI UC Berkeley

Abstract

Linear probing is a common technique in mechanistic interpretability despite the fact that the decodability of a given feature does not necessarily imply the network uses that feature. Intervention faithfulness, not merely decodability, is the appropriate criterion for whether a feature serves a defined active role in the model. Meanwhile, probe regularization has been used for feature discovery, but the impact of regularization on feature causality remains unclear. We study probe regularization systematically, starting with unregularized ordinary least squares (OLS) regression and considering increasing amounts of regularization via ridge regression. We show theoretically that OLS probes amplify low-variance directions in activation space that have spurious correlations with the target feature, whereas regularization reduces influence from these directions. Empirically, we find in a toy transformer and Llama-2-7B that intervention faithfulness increases up to a point, and then decreases again, and that the optimal regularization strength leads to features bearing striking similarity (in both direction and variance) to those learned by optimizing for intervention outcomes directly. Together, these results provide mechanistic justification for regularizing regression probes.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Towards Isolated Interventions via Almost Orthogonal Features in Language Models

    Feb 4, 2026Moritz Miller, Florent Draye, Bernhard SchölkopfDisentangled Representation LearningRepresentation Learning

  2. Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition

    Sep 16, 2026Devesh Tiwari, Camille Davis, Shivank Sinha +3Causal Interventions in Language ModelsHidden-State Probing

  3. Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language Models

    Sep 26, 2026Jonathan Drechsel, Steffen HerboldLLM InterpretabilityCausal Interventions in Language Models