finding
active
finding:predictive-code-shows-high-within-event-similarity-0-56-versus-across-0-04-while-saes-show-low-within-0-12-0-29

Predictive code shows high within-event similarity (0.56) versus across (-0.04), while SAEs show low within (0.12–0.29).

Fig. 7c over 50 GPT-5 stories.

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