# Trenton Bricken

Research and product · Interpretability at Anthropic

Designed his own Duke major in biological and artificial intelligence, then did a Harvard PhD in systems biology.

Full profile: https://www.autumn.ai/resources/anthropic/people/trenton-bricken

**At Anthropic:**
- Member of Technical Staff, interpretability
Sources: [1](https://matsprogram.org/mentor/bricken)

**Career before Anthropic:**
- Redwood Center for Theoretical Neuroscience, UC Berkeley, Visiting researcher
- Harvard Medical School, Debora Marks lab, PhD research in systems biology
- Duke University, Michael Lynch lab, Undergraduate research; graduated 2020
Sources: [1](https://matsprogram.org/mentor/bricken)

**Education:**
- PhD in Systems Biology from Harvard
- self-made major in "Minds and Machines: Biological and Artificial Intelligence" from Duke University in May 2020
Sources: [1](https://matsprogram.org/mentor/bricken)

**Lesser-known facts:**
- Was a visiting researcher at Berkeley's Redwood Center for Theoretical Neuroscience. [1](https://matsprogram.org/mentor/bricken)
- Spent a year in Michael Lynch's Duke lab using machine learning to design safer, more effective CRISPR guide RNAs. [1](https://www.trentonbricken.com/)
- Attended Duke as a Robertson Scholar, with full funding for all four years. [1](https://www.trentonbricken.com/)
- Wrote his Harvard thesis on sparse representations in biological and artificial neural networks. [1](https://www.trentonbricken.com/)
- Showed in a NeurIPS 2021 paper that transformer attention closely approximates Kanerva's Sparse Distributed Memory, a biologically plausible memory model. [1](https://arxiv.org/abs/2111.05498)
- Co-developed agents that audit models for misalignment; running many in parallel lifted one agent's solve rate from 13% to 42%. [1](https://alignment.anthropic.com/2025/automated-auditing/)
- Shoots analog film photography and keeps a site for his film photos. [1](https://www.trentonbricken.com/)

**Interviews and talks:**
- [Dwarkesh Podcast with Sholto Douglas: How LLMs actually think (2024)](https://www.dwarkesh.com/p/sholto-douglas-trenton-bricken)
- [Dwarkesh Podcast with Sholto Douglas: Is RL + LLMs enough for AGI? (2025)](https://www.dwarkesh.com/p/sholto-trenton-2)
- [Redwood Center for Theoretical Neuroscience seminar (2025)](https://redwood.berkeley.edu/seminars/trenton-bricken-apr-2025/)

**Known for:**
- Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs (2026)
- Findings from a Pilot Anthropic—OpenAI Alignment Evaluation Exercise (2025)
- Building and evaluating alignment auditing agents (2025)
- On the Biology of a Large Language Model (2025)
- Circuit Tracing: Revealing Computational Graphs in Language Models (2025)
- Auditing Language Models for Hidden Objectives (2025)
Sources: [1](https://www.trentonbricken.com/)

Researched with Autumn (https://www.autumn.ai) from public sources. Updated 2026-10-18. Everyone at Anthropic: https://www.autumn.ai/resources/anthropic/people