Chris Olah
Artificial Intelligence · 2015–2026
A researcher in the Science corpus: 25 papers; trusts 294 researchers and is trusted by 2,012 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 630 citations into it; #11,934 of 36,961 by trust here, #793 by citations
- Computer Vision and Pattern Recognition — 247 citations into it; #1,247 of 21,973 by trust here, #919 by citations
- Natural Language Processing — 153 citations into it; #5,072 of 5,725 by trust here, #2,456 by citations
- Generative Models — 69 citations into it; #240 of 1,963 by trust here, #231 by citations
- Representation & Self-Supervised Learning — 53 citations into it; #2,831 of 3,156 by trust here, #2,815 by citations
- Statistics and Probability — 25 citations into it
- Computational Theory and Mathematics — 23 citations into it
- Probabilistic & Bayesian Methods — 22 citations into it
Whom Chris Olah trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Alex Krizhevsky
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
- Kaiming He
- Tomas Mikolov
- Christian Szegedy
- Karen Simonyan
Who trusts Chris Olah overall
- Garrett Wilson
- Yoshua Bengio
- Andrea Vedaldi
- Ting-Li Chen
- Yang Song
- Christian Rupprecht
- Sergey I. Nikolenko
- Han Zhang
- Wes Gurnee
- Sergey Levine
Papers from Chris Olah's perspective
Ordered by how strongly the researchers Chris Olah trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Conditional Image Synthesis with Auxiliary Classifier GANs (2016) — 3,545 citations
- Concrete Problems in AI Safety (2016) — 3,295 citations
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (2022) — 4,254 citations
- Deconvolution and Checkerboard Artifacts (2016) — 1,756 citations
- A General Language Assistant as a Laboratory for Alignment (2021) — 1,175 citations
- Constitutional AI: Harmlessness from AI Feedback (2022) — 3,377 citations
- Inceptionism: Going Deeper into Neural Networks (2015) — 838 citations
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned (2022) — 837 citations
- Language Models (Mostly) Know What They Know (2022) — 1,782 citations
- Predictability and Surprise in Large Generative Models (2022) — 365 citations
- Is Generator Conditioning Causally Related to GAN Performance? (2018) — 124 citations
- In-context Learning and Induction Heads (2022) — 942 citations
- The Building Blocks of Interpretability (2018) — 735 citations
- Multimodal Neurons in Artificial Neural Networks (2021) — 412 citations
- The Capacity for Moral Self-Correction in Large Language Models (2023) — 214 citations
- Discovering Language Model Behaviors with Model-Written Evaluations (2022) — 917 citations
- Scaling Laws and Interpretability of Learning from Repeated Data (2022) — 166 citations
- Measuring Progress on Scalable Oversight for Large Language Models (2022) — 226 citations
- Toy Models of Superposition (2022) — 947 citations
- Zoom In: An Introduction to Circuits (2020) — 744 citations