Claims
Search the graph by meaning. Each result carries its current verdict; open one to see its decomposition, provenance, and the reasoning behind the assessment.
KindShowingImportancePrizesTopicAxBench
The AxBench benchmark for evaluating methods that elicit or steer representations in language models, including benchmark design, results, and comparisons among methods. Excludes unrelated benchmarks or representation-steering work not involving AxBench.
On AxBench, SAE steering underperforms both prompting and difference-in-means representations.
VerifiedThe evidence, examined directly, establishes the claim.constitution →empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →Mechanistic InterpretabilityAI Capability Evaluationimportance · minorImportance 0.40, 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 →
On AxBench, prompting and fine-tuning outperform SAE steering for eliciting specified concepts in language-model outputs.
UnassessedNo current assessment. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.constitution →empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →Large language modelsSparse Autoencodersimportance · notableImportance 0.45, from 0 to 1 · notable: a contested point in a live debate (also the default before judging). Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →
AxBench's concept-scoring judge sometimes assigns zero to generations whose labels match or closely relate to the elicited topic.
UnassessedNo current assessment. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.constitution →empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →LLM-as-a-JudgeAI Capability Evaluationimportance · minorImportance 0.30, 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 →
Contribute
If a claim here is wrong, or missing evidence, open it: every claim page carries its own entry for challenges, evidence, and corrections. If the graph is missing a claim or a question entirely, propose it below. A proposal is reviewed on its wording; accepted proposals are matched against the graph before they enter it.