pith. sign in

Interpretability in the wild: a circuit for indirect object identification in GPT-2 small

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

Dynamic Latent Routing

cs.LG · 2026-05-14 · unverdicted · novelty 7.0

Dynamic Latent Routing jointly learns discrete latent codes, routing policies, and model parameters via dynamic search to match or exceed supervised fine-tuning by 6.6 points on average in low-data settings across four datasets and six models.

citing papers explorer

Showing 2 of 2 citing papers.

  • Dynamic Latent Routing cs.LG · 2026-05-14 · unverdicted · none · ref 52

    Dynamic Latent Routing jointly learns discrete latent codes, routing policies, and model parameters via dynamic search to match or exceed supervised fine-tuning by 6.6 points on average in low-data settings across four datasets and six models.

  • Towards Effective Theory of LLMs: A Representation Learning Approach cs.LG · 2026-05-10 · unverdicted · none · ref 59

    RET learns temporally consistent macrovariables from LLM activations via self-supervised learning to support interpretability, early behavioral prediction, and causal intervention.