arXiv:2606. 27510v1 Announce Type: new Abstract: Activation patching is the primary tool in mechanistic interpretability.
arXiv:2607. 08349v1 Announce Type: new Abstract: Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components, or comparing a compressed model to the original one.
arXiv:2608. 03842v1 Announce Type: cross Abstract: When a language model fails on surface-perturbed input (typos, OCR noise, homophones), "which layer is responsible" has three natural operationalizations: where representations diverge most (sensitivity), where restoring clean activations recovers the prediction (causality), and where a small adapter can repair the damage (compensatory capacity) - and we show these three layer maps dissociate.
arXiv:2606. 10703v1 Announce Type: new Abstract: Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of targeted interventions on specific computations; in Pearl's terms, they treat rung-1 associational evidence as if it supported rung-2 interventional conclusions, a move whose validity is rarely tested.
arXiv:2606. 09899v1 Announce Type: cross Abstract: A central goal of mechanistic interpretability is to identify which internal components causally drive a language model's behavior.
arXiv:2606. 05378v1 Announce Type: new Abstract: We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families.
arXiv:2606. 19410v1 Announce Type: cross Abstract: Signed pairwise interaction scores fundamentally conflate uniqueness (U), redundancy (R), and synergy (S).
arXiv:2607. 01940v1 Announce Type: cross Abstract: Mechanistic interpretability often relies on component-level interventions to discover how a model produces a behavior.
arXiv:2605. 03268v2 Announce Type: replace-cross Abstract: Here we introduce Partially Observed Structural Causal Models (POSCMs) as an extension of structural causal models (SCMs) to settings where upstream contexts co-determine both the interaction structure and downstream mechanisms on observed variables.
arXiv:2606. 15779v1 Announce Type: cross Abstract: Multimodal models can name the action units (AUs) behind a facial emotion, but their AU->emotion rationales are typically plausible rather than faithful: nothing forces the AUs a model invokes to be the AUs that actually drive its prediction.
arXiv:2605. 23393v2 Announce Type: replace-cross Abstract: Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction.
arXiv:2607. 04334v1 Announce Type: new Abstract: Multimodal GUI agents read an interface through two redundant channels: the rendered pixels of a screenshot and a serialized structure such as a DOM or accessibility tree.
arXiv:2607. 05563v1 Announce Type: new Abstract: Interpretable explanation methods in Artificial Intelligence aim to uncover the underlying causes and their effects, enabling a deeper understanding of why a system behaves in a certain way under different inputs.