Alex Tamkin

Research Scientist

Alex is a research scientist at Anthropic. He completed his PhD in Computer Science at Stanford, advised by Noah Goodman, where he was an Open Philanthropy AI Fellow. His work focuses on understanding and controlling large pretrained language models.

NEWs & publications

Codebook Features: Sparse and Discrete Interpretability for Neural Networks
October 19, 2023
codebook-features-sparse-and-discrete-interpretability-for-neural-networks
Codebook Features: Sparse and Discrete Interpretability for Neural Networks
codebook-features-sparse-and-discrete-interpretability-for-neural-networks
Codebook Features: Sparse and Discrete Interpretability for Neural Networks
October 27, 2023
codebook-features-sparse-and-discrete-interpretability-for-neural-networks
Codebook Features: Sparse and Discrete Interpretability for Neural Networks
codebook-features-sparse-and-discrete-interpretability-for-neural-networks

publications:

No studies available yet.