CO
Chris Olah
cs.LGcs.AIcs.CLcs.CYcs.DC
On Valency
published · living versionsW_8nzh2mbs·v1 · currentpublished
In-context Learning and Induction Heads
with Catherine Olsson, Nelson Elhage, Neel Nanda, Nicholas Joseph +21
1 version
Preprints & journals
10 papers in the corpus · 2016–2026Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet2605.29358v1 · Adly Templeton, Tom Conerly, Jonathan Marcus et al.2026 · 0 citationsarXiv
Emotion Concepts and their Function in a Large Language Model2604.07729v1 · Nicholas Sofroniew, Isaac Kauvar, William Saunders et al.2026 · 4 citationsarXiv
When Models Manipulate Manifolds: The Geometry of a Counting Task2601.04480v1 · Wes Gurnee, Emmanuel Ameisen, Isaac Kauvar et al.2026 · 0 citationsarXiv
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned2209.07858v2 · Deep Ganguli, Liane Lovitt, Jackson Kernion et al.2022 · 119 citationsarXivon Valency
Language Models (Mostly) Know What They Know2207.05221v4 · Saurav Kadavath, Tom Conerly, Amanda Askell et al.2022 · 169 citationsarXivon Valency
In-context Learning and Induction Heads2209.11895v1 · Catherine Olsson, Nelson Elhage, Neel Nanda et al.2022 · 87 citationsarXivon Valency
Scaling Laws and Interpretability of Learning from Repeated Data2205.10487v1 · Danny Hernandez, Tom Brown, Tom Conerly et al.2022 · 22 citationsarXiv
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback2204.05862v1 · Yuntao Bai, Andy Jones, Kamal Ndousse et al.2022 · 389 citationsarXiv
A General Language Assistant as a Laboratory for Alignment2112.00861v3 · Amanda Askell, Yuntao Bai, Anna Chen et al.2021 · 27 citationsarXiv
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems1603.04467v2 · Mart'in Abadi, Ashish Agarwal, Paul Barham et al.2016 · 9,713 citationsarXivon Valency
Career total: 31 works. 10 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.