CO
Christopher Olah
cs.CLcs.LGcs.AIstat.MLcs.CVcs.CYcs.HC
On Valency
published · living versionsW_5uruupn8·v1 · currentpublished
Auditing language models for hidden objectives
with Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey +30
1 version
Preprints & journals
11 papers in the corpus · 2015–2025Auditing language models for hidden objectives2503.10965v2 · Samuel Marks, Johannes Treutlein, Trenton Bricken et al.2025 · 4 citationsarXivon Valency
The Capacity for Moral Self-Correction in Large Language Models2302.07459v2 · Deep Ganguli, Amanda Askell, Nicholas Schiefer et al.2023 · 53 citationsarXiv
Discovering Language Model Behaviors with Model-Written Evaluations2212.09251v1 · Ethan Perez, Sam Ringer, Kamil\.e Lukosi\=ut\.e et al.2022 · 224 citationsarXivon Valency
Constitutional AI: Harmlessness from AI Feedback2212.08073v1 · Yuntao Bai, Saurav Kadavath, Sandipan Kundu et al.2022 · 322 citationsarXivon Valency
Measuring Progress on Scalable Oversight for Large Language Models2211.03540v2 · Samuel R. Bowman, Jeeyoon Hyun, Ethan Perez et al.2022 · 34 citationsarXiv
Predictability and Surprise in Large Generative Models2202.07785v2 · Deep Ganguli, Danny Hernandez, Liane Lovitt et al.2022 · 204 citationsarXiv
Toy Models of Superposition2209.10652v1 · Nelson Elhage, Tristan Hume, Catherine Olsson et al.2022 · 49 citationsarXiv
Is Generator Conditioning Causally Related to GAN Performance?1802.08768v2 · Augustus Odena, Jacob Buckman, Catherine Olsson et al.2018 · 48 citationsarXiv
Conditional Image Synthesis With Auxiliary Classifier GANs1610.09585v4 · Augustus Odena, Christopher Olah, Jonathon Shlens2016 · 2,033 citationsarXivon Valency
Changing Model Behavior at Test-Time Using Reinforcement Learning1702.07780v1 · Augustus Odena, Dieterich Lawson, Christopher Olah2017 · 18 citationsarXiv
Document Embedding with Paragraph Vectors1507.07998v1 · Andrew M. Dai, Christopher Olah, Quoc V. Le2015 · 263 citationsarXiv
Career total: 13 works. 11 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.