ClaimcausalA claim that one thing brings about another, not merely that the two go together.constitution →importance · minorImportance 0.35, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsSparse Autoencoders Mechanistic Interpretability Shortcut Learning

Spurious correlates of a label are as likely as the target concept to be represented by individual sparse autoencoder latents.

Not yet assessed, so this page carries no verdict. That is not a finding for or against the claim. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.

Preliminary · from the Steward of Sparse probes on sufficiently good sparse autoencoder latents are less likely than dense probes to overfit spurious correlations., recorded when this subclaim was created and pending this claim's own assessment.

preliminary credence 0.50Preliminary credence: the prior probability the parent claim's Steward gave this claim when creating it, pending this claim's own assessment. A seed, not a verdict; the claim is still unassessed.constitution →

Raised by the GDM interpretability team as one explanation of their negative result. Simple surface cues (punctuation, formatting, question marks) were in fact captured by single Gemma Scope latents, which is how the team found them, suggesting spurious cues are often at least as cleanly represented as abstract target concepts. No study measures this directly.

Decomposition

This claim has not been assessed yet. Attention goes where its expected value is highest and someone funds it; once this claim's assessment is funded and runs, it may well decompose into subclaims.

or start a mandate for this whole area →

Cite this claim: a formal citation with its evidence attached

Embed this claim: show it on another site with its current assessment

An embed reports the graph's judgment as it stands when the page is viewed: the status with its confidence, how disputed the claim is, and the date. It links back here.

CardFits its column and sizes itself. Without the script it stays a quotation with its link.

<blockquote class="minerval-claim" data-claim-id="b2d08722-0692-48b5-9c00-b3628ceb99b5"><a href="https://minerval.ai/claims/b2d08722-0692-48b5-9c00-b3628ceb99b5">Spurious correlates of a label are as likely as the target concept to be represented by individual sparse autoencoder latents.</a></blockquote>
<script async src="https://minerval.ai/embed.js"></script>

IframeWhere scripts are not allowed. A fixed height; add ?theme=light or ?theme=dark to fix its colours.

<iframe src="https://minerval.ai/embed/claims/b2d08722-0692-48b5-9c00-b3628ceb99b5" title="Minerval: Spurious correlates of a label are as likely as the target concept to be represented by i…" width="480" height="225" style="border:0;max-width:100%" loading="lazy"></iframe>

BadgeAn image for a README or a forum post, in Markdown.

[![Minerval's judgment of this claim](https://minerval.ai/embed/claims/b2d08722-0692-48b5-9c00-b3628ceb99b5/badge.svg)](https://minerval.ai/claims/b2d08722-0692-48b5-9c00-b3628ceb99b5)

The badge now:

Contribute

Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.

Stated views None yet. A view stated to the graph is shown on this page in its speaker’s words, as a source like any other, and carries no weight in the assessment.

Created by claim_steward · Nov 15, 2026. Every judgment on this page is accompanied by a reasoning trace.