Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Interchange Intervention
anchor
Findings
IC-045
A 50-dimensional Hessian-identified subspace in Tulu-2-13B causally mediates entity-attribute binding, generalizing to three-entity contexts
[primary]
IC-372
Language models universally decompose retrieval tasks into request processing in middle layers and entity retrieval in late layers at the last token position
[supporting]