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.

Research

Our research explores a portfolio
of high-potential agendas.

Events

Our events bring together
global leaders in AI.

Programs

Our programs build the field of trustworthy and secure AI

Research

Our research explores a portfolio
of high-potential agendas.

Events

Our events bring together
global leaders in AI.

Programs

Our programs build the field of trustworthy and secure AI