Chris Olah

Publications by Year

Research Areas

Topic Modeling, Natural Language Processing Techniques, Adversarial Robustness in Machine Learning, Neural Networks and Applications, Explainable Artificial Intelligence (XAI)

Most-Cited Works

• → TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems(2016)9,726 cited
• → Deconvolution and Checkerboard Artifacts(2016)1,638 cited
• → Feature Visualization(2017)803 cited
• → The Building Blocks of Interpretability(2018)603 cited
• → Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback(2022)360 cited
• → Zoom In: An Introduction to Circuits(2020)242 cited
• → Multimodal Neurons in Artificial Neural Networks(2021)213 cited
• → Language Models (Mostly) Know What They Know(2022)159 cited
• → Activation Atlas(2019)135 cited
• → Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned(2022)99 cited