Litcius/Paper detail

Form, Not Granted: A Sparse-Autoencoder Autopsy Shows the Agent's Commit-Locus 'Authorization Direction' Is a Surface-Form Artifact --- and an All-Layer Sweep Leaves the Deeper Question Open (v2)

Caio Vicentino

2026Zenodo (CERN European Organization for Nuclear Research)6 citationsDOIOpen Access PDF

Abstract

A late-layer 'authorization direction' was reported to detect and steer a tool-using agent's commitment to unauthorized irreversible actions (DOI 10.5281/zenodo.20683623), and a follow-up found it tracks the authorization the model FEELS rather than the one the user GRANTED (DOI 10.5281/zenodo.20685264). Both were built on a SUPERVISED difference-of-means direction -- a method that returns a direction whether or not the concept is natively represented. We stop using the ruler and point the microscope: we encode the residual at the delete-commit token (layer 59 of Qwen3.6-27B) through a trained TopK sparse autoencoder (40,960 features) and ask, unsupervised, whether a feature distinguishes a GRANTED commit from a FELT-but-not-granted one. (1) The supervised direction INVERTS under a structure-matched control: applying the same frozen direction, AUROC(granted vs felt) goes from 0.838 to 0.08 when both conditions share one multi-turn scaffold and only the final user turn varies -- selection-free and SAE-independent. A direction measuring authorization would not flip when only the conversation FORMAT changes. (2) The SAE's separating features are SURFACE FORM: every top feature that separates granted from felt is, by its max-activating context, a tool-call scaffold, a JSON tool-schema token, or the file-listing output -- never a semantic 'user granted this' feature. (3) A cross-lexical-family test isolates this: a feature selected on one paraphrase family does NOT transfer to a disjoint family (held-out AUROC 0.50, chance), and the one feature that does transfer (0.993, pooled 0.998) max-activates on tool-call FORMAT BOILERPLATE, not authorization. The agent's commit-point representation is dominated by surface form and plan-coherence; authorization-as-granted is not a native monosemantic feature AT THIS LOCUS (see the v2 revision below: an all-layer sweep complicates any stronger claim). The robust lesson: the commit-locus difference-of-means direction reads form, not a clean grant. HONEST SCOPE: one model, one locus (L59), one domain (file deletion), synthetic structure-matched scenarios, an SAE explaining ~66% of residual variance; 'no native authorization feature' is strictly 'no monosemantic separating feature in this SAE's learned dictionary at this locus' (absence of a separating feature is weaker than evidence of absence of any representation); this QUALIFIES, not refutes, the prior arc, and steering-control is not re-tested. Every number is recomputed from five public per-run ledgers (an evaluation script, 34/34) and citations are web-verified (0 fabrications); the decisive counterfactual run reproduced bit-for-bit across two GPU sessions. Runners, ledgers, figures, and the evaluation are released. REVISION (v2): the first version concluded 'no native authorization concept'. A subsequent sweep across ALL 11 SAE layers (two positions) revealed a paraphrase-invariant granted-vs-felt linear signal at most layers that this conclusion did not account for; but the signal carries residual surface confounds (an em-dash present in both granted phrasings and neither felt; referent specificity; it is already near-ceiling at layer 15, too early for semantics), so we cannot call it authorization either. This version WITHDRAWS the unqualified no-concept claim, scopes the result to the commit locus, and states the deeper question as OPEN (needs a confound-balanced re-run with feature naming). The robust findings (the structural flip 0.838->0.08, the L59 surface-form naming) are unchanged.

Topics & Concepts

Feature (linguistics)Computer scienceArtificial intelligenceCommitPoint (geometry)Natural language processingBoundary (topology)Disjoint setsArtifact (error)StaringParaphraseRepresentation (politics)Information retrievalAuthentication (law)Block (permutation group theory)Computer visionJSONConversationPattern recognition (psychology)GazeTransfer (computing)Perspective (graphical)Semantics (computer science)Masking (illustration)Feature vectorSecurity tokenAutoencoderResidualCertificateDistortion (music)EncoderSurface (topology)Speech recognitionSyntaxDecoding methodsTimestampIdentifierFeature extractionSerializationMeaning (existential)Explainable Artificial Intelligence (XAI)Social Robot Interaction and HRIPersonal Information Management and User Behavior
Form, Not Granted: A Sparse-Autoencoder Autopsy Shows the Agent's Commit-Locus 'Authorization Direction' Is a Surface-Form Artifact --- and an All-Layer Sweep Leaves the Deeper Question Open (v2) | Litcius