C. Olah

发表

Concrete Problems in AI Safety pdf

John Schulman, Dario Amodei, Chris Olah, 2016, ArXiv.

Inceptionism: Going Deeper into Neural Networks

Alexander Mordvintsev, Mike Tyka, Christopher Olah, 2015 .

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems pdf

Martín Abadi, Martin Wattenberg, Michael Isard, 2016, ArXiv.

Document Embedding with Paragraph Vectors pdf

Quoc V. Le, Andrew M. Dai, Christopher Olah, 2015, ArXiv.

Activation Atlas

C. Olah, Shan Carter, Zan Armstrong, 2019, Distill.

Conditional Image Synthesis with Auxiliary Classifier GANs

Jonathon Shlens, Augustus Odena, Christopher Olah, 2016, ICML.

Deconvolution and Checkerboard Artifacts

Vincent Dumoulin, Augustus Odena, Christopher Olah, 2016 .

C ONDITIONAL I MAGE S YNTHESIS WITH A UXILIARY C LASSIFIER GAN S

Jonathon Shlens, C. Olah, Augustus Odena, 2016 .

TensorFlow Distributions Joshua

Andy Davis, Geoffrey Irving, Dandelion Mané, 2017 .

ZiMM: a deep learning model for long term adverse events with non-clinical claims data

Ilya, Geoffrey Irving, Dandelion Mané, 2019 .

Differentiable Image Parameterizations

Nicola Pezzotti, Alexander Mordvintsev, Christopher Olah, 2018, Distill.

The Building Blocks of Interpretability

Arvind Satyanarayan, Ian Johnson, Alexander Mordvintsev, 2018 .

The Paths Perspective on Value Learning

Sam Greydanus, Chris Olah, C. Olah, 2019, Distill.

A Closer Look at Gradient Estimators with Reinforcement Learning as Inference

Ilya Sutskever, Jonathon Shlens, C. Olah, 2021 .

Scaling Laws and Interpretability of Learning from Repeated Data

Tom B. Brown, Dario Amodei, T. Henighan, 2022, ArXiv.

Neural Guidance for SAT Solving

Andy Davis, Geoffrey Irving, Yangqing Jia, 2018 .

Language Models (Mostly) Know What They Know

Tom B. Brown, Dario Amodei, T. Henighan, 2022, ArXiv.

Zoom In: An Introduction to Circuits

Nick Cammarata, Shan Carter, Gabriel Goh, 2020 .

Thread: Circuits

Nick Cammarata, Shan Carter, Gabriel Goh, 2020, Distill.

In-context Learning and Induction Heads

Tom B. Brown, Dario Amodei, T. Henighan, 2022, ArXiv.

Predictability and Surprise in Large Generative Models

Tom B. Brown, Dario Amodei, T. Henighan, 2022, FAccT.

Multimodal Neurons in Artificial Neural Networks

Alec Radford, Nick Cammarata, Shan Carter, 2021 .

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Tom B. Brown, Dario Amodei, T. Henighan, 2022, ArXiv.

Naturally Occurring Equivariance in Neural Networks

C. Olah, Ludwig Schubert, Gabriel Goh, 2020 .

Toy Models of Superposition

Dario Amodei, T. Henighan, Sam McCandlish, 2022, ArXiv.

Experiments in Handwriting with a Neural Network

Ian Johnson, Shan Carter, David Ha, 2016 .

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Tom B. Brown, Dario Amodei, T. Henighan, 2022, ArXiv.

Measuring Progress on Scalable Oversight for Large Language Models

Tom B. Brown, Dario Amodei, Azalia Mirhoseini, 2022, ArXiv.

Discovering Language Model Behaviors with Model-Written Evaluations

Tom B. Brown, Dario Amodei, T. Henighan, 2022, ACL.

Understanding RL vision

Jacob Hilton, Nick Cammarata, Shan Carter, 2020 .

An Overview of Early Vision in InceptionV1

Nick Cammarata, Shan Carter, Gabriel Goh, 2020 .

Is Generator Conditioning Causally Related to GAN Performance? pdf

Colin Raffel, Ian J. Goodfellow, Augustus Odena, 2018, ICML.

A General Language Assistant as a Laboratory for Alignment pdf

Dario Amodei, Tom Henighan, Tom B. Brown, 2021, ArXiv.

High/Low frequency detectors

Ludwig Schubert, Chelsea Voss, Chris Olah, 2021 .

The Capacity for Moral Self-Correction in Large Language Models

Tom B. Brown, Dario Amodei, Azalia Mirhoseini, 2023, ArXiv.

Constitutional AI: Harmlessness from AI Feedback

Tom B. Brown, Dario Amodei, Azalia Mirhoseini, 2022, ArXiv.

Language Models (Mostly) Know What They Know

Tom B. Brown, Dario Amodei, T. Henighan, 2022, ArXiv.

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Tom B. Brown, Dario Amodei, T. Henighan, 2022, ArXiv.

Rethinking the modeling of the instrumental response of telescopes with a differentiable optical model

Ilya Sutskever, Jonathon Shlens, Sherry Moore, 2021 .

Curve Detectors

C. Olah, Shan Carter, Ludwig Schubert, 2020, Distill.

Visualizing Weights

C. Olah, Ludwig Schubert, Gabriel Goh, 2021, Distill.

Branch Specialization

C. Olah, Ludwig Schubert, Gabriel Goh, 2022, Distill.

Predictability and Surprise in Large Generative Models

Tom B. Brown, Dario Amodei, T. Henighan, 2022, FAccT.

Changing Model Behavior at Test-Time Using Reinforcement Learning pdf

Augustus Odena, Christopher Olah, Dieterich Lawson, 2017, ICLR.