Reverse engineering neural networks at @AnthropicAI. Previously @distillpub, OpenAI Clarity Team, Google Brain. Personal account.
Chris Olah is a machine learning researcher and Anthropic co-founder known for pioneering mechanistic interpretability and neural network visualization techniques. Tagged AI Safety because his primary work centers on reverse engineering models for understanding and alignment.
Public Tech-ranked followers appear first; other tracked followers remain below.
Last updated 13d ago · 2087 influencers tracked · 2000 ranked users