LG
Leo Gao
cs.CLcs.LGcs.AIstat.MLcs.CYcs.NE
On Valency
published · living versionsW_b2ety6g8·v1 · currentpublished
Scaling and evaluating sparse autoencoders
with Tom Dupré la Tour, Henk Tillman, Gabriel Goh, Rajan Troll +4
1 version
Preprints & journals
15 papers in the corpus · 2020–2025Lessons from the Trenches on Reproducible Evaluation of Language Models2405.14782v3 · Stella Biderman, Hailey Schoelkopf, Lintang Sutawika et al.2024 · 5 citationsarXiv
Weight-sparse transformers have interpretable circuits2511.13653v1 · Leo Gao, Achyuta Rajaram, Jacob Coxon et al.2025 · 0 citationsarXiv
Scaling and evaluating sparse autoencoders2406.04093v1 · Leo Gao, Tom Dupr'e la Tour, Henk Tillman et al.2024 · 11 citationsarXivon Valency
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision2312.09390v1 · Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner et al.2023 · 25 citationsarXiv
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model2211.05100v4 · BigScience Workshop: Teven Le Scao, Angela Fan, Christopher Akiki et al.2022 · 834 citationsarXiv
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models2206.04615v3 · Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao et al.2022 · 565 citationsTransactions on Machine Learning Research, May/2022, https://openreview.net/forum?id=uyTL5Bvosj
Scaling Laws for Reward Model Overoptimization2210.10760v1 · Leo Gao, John Schulman, Jacob Hilton2022 · 34 citationsarXiv
EleutherAI: Going Beyond "Open Science" to "Science in the Open"2210.06413v1 · Jason Phang, Herbie Bradley, Leo Gao et al.2022 · 3 citationsarXiv
GPT-NeoX-20B: An Open-Source Autoregressive Language Model2204.06745v1 · Sid Black, Stella Biderman, Eric Hallahan et al.2022 · 479 citationsarXiv
Multitask Prompted Training Enables Zero-Shot Task Generalization2110.08207v3 · Victor Sanh, Albert Webson, Colin Raffel et al.2021 · 563 citationsarXiv
Datasheet for the Pile2201.07311v1 · Stella Biderman, Kieran Bicheno, Leo Gao2022 · 0 citationsarXiv
Cut the CARP: Fishing for zero-shot story evaluation2110.03111v3 · Shahbuland Matiana, JR Smith, Ryan Teehan et al.2021 · 0 citationsarXiv
An Empirical Exploration in Quality Filtering of Text Data2109.00698v2 · Leo Gao2021 · 2 citationsarXiv
The Pile: An 800GB Dataset of Diverse Text for Language Modeling2101.00027v1 · Leo Gao, Stella Biderman, Sid Black et al.2020 · 475 citationsarXiv
Collaborative Storytelling with Large-scale Neural Language Models2011.10208v1 · Eric Nichols, Leo Gao, Randy Gomez2020 · 49 citationsarXiv
Career total: 26 works. 15 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.