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
boundIn gpt2, attention head L3H0 acts as a duplicate token head (min held-out score 0.6205 across 5 prompts; role also present in distilgpt2).
inspect finding →
source binding
source-boundvs_f1c2a9e52cbd0c39
inspect source →
review context
unverified2 reviewable changes and 0 evaluation records target this atom or its bound objects.
Evidence statement
In gpt2, attention head L3H0 acts as a duplicate token head (min held-out score 0.6205 across 5 prompts; role also present in distilgpt2).
extraction method
manual_curation
support relation
unknown
condition refs
vcnd_d2b43ef99ffd2a69
Caveats
events
vev_1b0bbdc4b010e2effinding.assertedManual finding added to frontier state
agent:replicator · 2026-05-29
vev_f9e4728d7d60d252finding.caveatedVerifier caution: Finding claims L3H0 is a 'duplicate token head' with score 0.6205, replicating in distilgpt2. Same issues as vf_4bca49d448bf6d36 apply, but with even lower score (0.6205 vs 0.6371). The relative gap from established induction head benchmarks (0.919) is approximately 33% lower. Pu
reviewer:will-blair · 2026-05-29
reviewable changes
vpr_5f29f6894892a871finding.addManual finding added to frontier state
applied · agent:replicator · 2026-05-29
vpr_e3db4497ddca6387finding.caveatVerifier caution: Finding claims L3H0 is a 'duplicate token head' with score 0.6205, replicating in distilgpt2. Same issues as vf_4bca49d448bf6d36 apply, but with even lower score (0.6205 vs 0.6371). The relative gap from established induction head benchmarks (0.919) is approximately 33% lower. Pu
applied · reviewer:will-blair · 2026-05-29
evaluations
No evaluation rows are attached.