Future Lens: Anticipating Subsequent Tokens from a Single Hidden State (2023 · 49 citations)
The paper asks whether a transformer's internal state for one token carries information about tokens beyond the immediate next one, specifically positions t+2 and later. Working with GPT-J-6B, the authors compare three ways of reading that information out of a single hidden state taken at one layer and one position.
The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis (2026 · 7 citations)
Research on mechanistic interpretability (MI) of language models is fragmented. Studies use bespoke evaluations, lack a shared theoretical basis, and rarely define the elementary causal units that make up a "mechanism." This survey, published in Computational Linguistics, treats MI as recovering causal graphs that…

All works

4 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Future Lens: Anticipating Subsequent Tokens from a Single Hidden StateConference on Computational Natural Language Learning (CoNLL)Koyena Pal, Jiuding Sun, Andrew Yuan, et al.2023 · 49 citations
The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation AnalysisComputational LinguisticsAaron Mueller, Jannik Brinkmann, Millicent Li, et al.2026 · 7 citations
HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks ↗arXiv (Cornell University) · no summary yetJiuding Sun et al.2025 · 4 citations
Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces ↗arXiv (Cornell University) · no summary yetSimon Yu et al.2026

Co-authors here

6 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 49 times (of the 149,439 papers whose bibliographies we read); 6 citing papers with a page here →.

Updated 30 October 2026