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
boundAcross all five transformers (gpt2, distilgpt2, pythia-70m, pythia-160m, gpt2-medium), the in-context-repetition circuit is universal and stereotyped by depth: duplicate-token heads emerge shallowest (layers 0-1), previous-token heads at early-to-mid depth, and induction heads in the middle-to-deep band (~30-90% relative depth); the induction-head group is causally necessary in every model (group-ablation delta 4.95-11.52 nats, all per-seed deltas positive).
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
Across all five transformers (gpt2, distilgpt2, pythia-70m, pythia-160m, gpt2-medium), the in-context-repetition circuit is universal and stereotyped by depth: duplicate-token heads emerge shallowest (layers 0-1), previous-token heads at early-to-mid depth, and induction heads in the middle-to-deep band (~30-90% relative depth); the induction-head group is causally necessary in every model (group-ablation delta 4.95-11.52 nats, all per-seed deltas positive).
extraction method
manual_curation
support relation
unknown
condition refs
vcnd_bc2bc22579a50d8c
Caveats
events
vev_0e2ce4e5ffa52f6cfinding.assertedManual finding added to frontier state
agent:replicator · 2026-05-29
vev_833001ee0ddf660cfinding.caveatedVerifier caution: The core claim—that a group of induction heads is causally necessary across 5 models—is valid and well-supported by the repeated-token ablation. However, the language significantly overstates the scope: 'universal' and 'stereotyped by depth' imply properties across tasks, archite
reviewer:will-blair · 2026-05-29
reviewable changes
vpr_23db2dbfd9b1e369finding.addManual finding added to frontier state
applied · agent:replicator · 2026-05-29
vpr_3906611ccc2f44e6finding.caveatVerifier caution: The core claim—that a group of induction heads is causally necessary across 5 models—is valid and well-supported by the repeated-token ablation. However, the language significantly overstates the scope: 'universal' and 'stereotyped by depth' imply properties across tasks, archite
applied · reviewer:will-blair · 2026-05-29
evaluations
No evaluation rows are attached.