Catherine Olsson
E1042653
Catherine Olsson is a researcher and entrepreneur known for her work in AI safety and interpretability, including co-founding the AI company Anthropic.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Catherine Olsson canonical | 1 |
Statements (46)
| Predicate | Object |
|---|---|
| instanceOf |
AI researcher
ⓘ
artificial intelligence company ⓘ entrepreneur ⓘ person ⓘ |
| coFounderOf | Anthropic NERFINISHED ⓘ |
| countryOfCitizenship | United States of America ⓘ |
| educatedAt |
Massachusetts Institute of Technology
ⓘ
New York University ⓘ |
| employer |
Anthropic
NERFINISHED
ⓘ
Google ⓘ OpenAI NERFINISHED ⓘ |
| fieldOfStudy |
computer science
ⓘ
machine learning ⓘ neural networks ⓘ |
| fieldOfWork |
AI interpretability
ⓘ
AI safety ⓘ AI safety ⓘ artificial intelligence ⓘ artificial intelligence ⓘ |
| hasAcademicAdvisor |
Samy Bengio
NERFINISHED
ⓘ
Yann LeCun NERFINISHED ⓘ |
| hasActivity |
contributing to public discourse on AI safety
ⓘ
publishing AI research papers ⓘ speaking at AI conferences ⓘ |
| hasGender | female ⓘ |
| hasResearchInterest |
alignment of advanced AI systems
ⓘ
interpretability tools for deep learning ⓘ robustness of neural networks ⓘ safety of large-scale language models ⓘ |
| hasRole |
co-founder of Anthropic
ⓘ
research scientist at OpenAI ⓘ researcher at Anthropic ⓘ software engineer at Google ⓘ |
| knownFor |
co-founding Anthropic
ⓘ
work on AI safety ⓘ work on interpretability of neural networks ⓘ |
| languageSpoken | English ⓘ |
| memberOf |
AI safety research community
ⓘ
machine learning research community ⓘ |
| notableWork |
research on safety properties of large language models
ⓘ
research on understanding internal representations of neural networks ⓘ |
| workedAt |
Google
NERFINISHED
ⓘ
OpenAI NERFINISHED ⓘ |
| workedOn |
feature visualization in neural networks
ⓘ
mechanistic interpretability ⓘ neural network interpretability ⓘ |
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.