What are the responsibilities and job description for the Research Scientist, Interpretability position at Anthropic?
About the role:
Some of our team's notable publications include A Mathematical Framework for Transformer Circuits, In-context Learning and Induction Heads, and Toy Models of Superposition. This work builds on ideas from members' work prior to Anthropic such as the original circuits thread, Multimodal Neurons, Activation Atlases, and Building Blocks.
We aim to create a solid foundation for mechanistically understanding neural networks and making them safe (see our vision post). In the short term, we have focused on resolving the issue of "superposition" (see Toy Models of Superposition, Superposition, Memorization, and Double Descent, and our May 2023 update), which causes the computational units of the models, like neurons and attention heads, to be individually uninterpretable, and on finding ways to decompose models into more interpretable components. Our recent work finding millions of features on Sonnet, one of our production language models, represents progress in this direction. This is a stepping stone towards our overall goal of mechanistically understanding neural networks.
We often collaborate with teams across Anthropic, such as Alignment Science and Societal Impacts to use our work to make Anthropic’s models safer. We also have an Interpretability Architectures project that involves collaborating with Pretraining. If you would be especially excited to work on a project that touches upon the intersection of Interpretability and another team, feel free to note down the specific team(s) you’d be interested in collaborating with.Responsibilities:
- Develop methods for understanding LLMs by reverse engineering algorithms learned in their weights
- Design and run robust experiments, both quickly in toy scenarios and at scale in large models
- Build infrastructure for running experiments and visualizing results
- Work with colleagues to communicate results internally and publicly
You may be a good fit if you:
- Have a strong track record of scientific research (in any field), and have done some work on Interpretability
- Enjoy team science – working collaboratively to make big discoveries
- Are comfortable with messy experimental science. We're inventing the field as we work, and the first textbook is years away
- You view research and engineering as two sides of the same coin. Every team member writes code, designs and runs experiments, and interprets results
- You can clearly articulate and discuss the motivations behind your work, and teach us about what you've learned. You like writing up and communicating your results, even when they're null
