Pith. sign in

Reading tea leaves: How humans interpret topic models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Evaluating SAE interpretability without explanations

cs.LG · 2025-07-11 · conditional · novelty 5.0

SAE latent interpretability can be scored directly from activation examples via intruder detection and embedding clustering, with LLM scores correlating strongly with human scores.

citing papers explorer

Showing 1 of 1 citing paper.

  • Evaluating SAE interpretability without explanations cs.LG · 2025-07-11 · conditional · none · ref 6

    SAE latent interpretability can be scored directly from activation examples via intruder detection and embedding clustering, with LLM scores correlating strongly with human scores.