Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models

Mechanistic interpretability project that localizes entity-selective neurons (“entity cells”) in language models and uses causal interventions on PopQA-style factual question answering to study how these neurons mediate entity-centric factual recall.

Endorsements support MentaLeap.

No endorsements yet.

Discussion

Start Date

-

End Date

-

Expected Duration

-

Funding Raised to Date

-