Interpretability
18 people are listed under this topic in the USASI directory. Most common companies: Anthropic (3), IBM (3), Georgia Institute of Technology (2), Cohere (1), Google DeepMind (1).
Top companies in Interpretability
- Anthropic 3
- IBM 3
- Georgia Institute of Technology 2
- Cohere 1
- Google DeepMind 1
- Irvine 1
- MIT 1
- National Deep Inference Fabric 1
- Northeastern University 1
- Pencil Code 1
- Profluent 1
- Spiffy AI 1
People
- Aeree ChoMachine learning PhD student in the Polo Club of Data Science (since fall 2024) · Georgia Institute of Technology
- Aleksandra MojsilovićBuilders & open source
- Arthur ConmyMember of Technical Staff · Anthropic
- Carlos GuestrinProfessor, Computer Science; Fortinet Founders Professor and Senior Fellow at the Stanford Institute for Human-Centered AI · Stanford University
- Chris OlahCo-founder · Anthropic
- David BauAssistant Professor of Computer Science · Northeastern University (Khoury College of Computer Sciences)
- Duen Horng "Polo" ChauProfessor and Associate Chair, School of Computational Science and Engineering; Associate Director, MS in Analytics · Georgia Institute of Technology
- Hendrik StrobeltSenior Research Scientist; Explainability Lead, MIT-IBM Watson AI Lab · IBM Research
- Jacob AndreasAssociate Professor · Massachusetts Institute of Technology (EECS and CSAIL)
- Jacob SteinhardtAssociate Professor of Statistics and EECS · University of California, Berkeley
- Kenneth LiResearcher · Thinking Machines Lab
- Kush R. VarshneyIBM Fellow, directing Human-Centered Trustworthy AI research · IBM Research
- Michael HindDistinguished Research Staff Member · IBM Research
- Neel NandaRuns the mechanistic interpretability team · Google DeepMind
- Nick FrosstCo-founder · Cohere
- Sameer SinghProfessor, Department of Computer Science, University of California · Irvine
- Samuel MarksMember of Technical Staff; leads the Cognitive Oversight subteam of the Alignment Science team · Anthropic
- Sarthak JainMachine learning team member · Profluent
Other topics: Language models · Teaching and writing · Developer tools · Agents · ML frameworks and libraries · Datasets and data · Training systems · Evaluation and benchmarks · Inference and serving · Chips and hardware · Computer vision · Image, video, and 3D generation · Safety and alignment · Reinforcement learning · Multimodal models · AI for science · Speech and audio · Robotics · Machine-learning theory