question
active
question:can-latent-codes-from-saes-or-temporal-feature-analyzers-capture-the-in-context-graph-phenomenon

Can latent codes from SAEs or Temporal Feature Analyzers capture the in-context graph phenomenon?

§6.3 question.

Source paper

extracted_from
Priors in Time: Missing Inductive Biases for Language Model Interpretability
(2025) · Lubana, Ekdeep Singh · Rager, Can · Hindupur, Sai Sumedh R. · Costa, Valerie +12

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.