Scholar
Curt Tigges
Google Scholar ID: jjYEqfcAAAAJ
Science Lead, Decode Research
Citations & Impact
Citations
236
H-index
6
i10-index
6
Publications
7
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Published research on evaluating SAEs, analyzing the evolution and consistency of LLM circuits, and finding evidence for the linear representation hypothesis. He has also written several articles such as 'Prioritizing AI Welfare Means Prioritizing Consciousness' and 'Lasering Your Brain for Fun and Profit'.
Research Experience
- Currently a researcher at Goodfire AI, focusing on mechanistic interpretability; previously worked at Decode Research on building open-source tools and replications of key mech interp techniques, as well as scientific direction and feature building for Neuronpedia.
Background
- Research interests include life design, mechanistic interpretability, learning, philosophy, and consciousness. He believes that the decisions we make in the next few years and decades will have a profound effect on the future of sentient life.
Miscellany
- Lived in San Francisco for the past two years, enjoys attending or hosting social, cultural, and intellectual events, reading, cooking, exploring food sources and farms, amateur astronomy, learning languages, and spending time in the wilderness. He has lived in Taiwan and Japan in the past and draws inspiration from their cities and cultures.
Co-authors