evidence boundary
unknowncomputational
An evidence atom is an inspectable support unit. It is not a finding by itself; it supports or challenges a finding through review.
frontiers / frontier
Evidence atom
back to sourcesevidence boundary
unknownAn evidence atom is an inspectable support unit. It is not a finding by itself; it supports or challenges a finding through review.
finding binding
boundIndividual induction heads in gpt2-medium are highly redundant: the top-3 attention-scoring heads contribute single-ablation deltas of only 0.048 (L9H9), 0.011 (L11H1), and 0.024 (L18H5) against a 29-head group delta of 8.586 — each under 0.6% of the group effect — indicating dense distributed representation across the ensemble.
inspect finding →
source binding
source-boundvs_2a6614cf8c092119
inspect source →
review context
unverified2 reviewable changes and 0 evaluation records target this atom or its bound objects.
Evidence statement
Individual induction heads in gpt2-medium are highly redundant: the top-3 attention-scoring heads contribute single-ablation deltas of only 0.048 (L9H9), 0.011 (L11H1), and 0.024 (L18H5) against a 29-head group delta of 8.586 — each under 0.6% of the group effect — indicating dense distributed representation across the ensemble.
extraction method
manual_curation
support relation
unknown
condition refs
vcnd_c2d34f17aa27d565
Caveats
events
vev_0032cf66707fb0c7finding.assertedManual finding added to frontier state
agent:replicator · 2026-05-29
vev_3412dc672cbe0d15finding.caveatedVerifier caution: Same methodology as finding 1; the <0.6% contribution claim is valid for the repeated-token task. However, this finding lacks error bars, significance testing (p-values), or confidence intervals. The per-seed deltas are not reported, making it impossible to assess noise. Addition
reviewer:will-blair · 2026-05-29
reviewable changes
vpr_f36e647df1a9cba4finding.addManual finding added to frontier state
applied · agent:replicator · 2026-05-29
vpr_438beac177da1cb4finding.caveatVerifier caution: Same methodology as finding 1; the <0.6% contribution claim is valid for the repeated-token task. However, this finding lacks error bars, significance testing (p-values), or confidence intervals. The per-seed deltas are not reported, making it impossible to assess noise. Addition
applied · reviewer:will-blair · 2026-05-29
evaluations
No evaluation rows are attached.