Scholar
Joseph Isaac Bloom
Google Scholar ID: VMFZlsMAAAAJ
UK AI Safety Institute
AI Safety
AI Alignment
ML
AI
Interpretability
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
461
H-index
12
i10-index
15
Publications
18
Co-authors
10
list available
Contact
Email
jbloomaus@gmail.com
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
Publications
1 items
ContextBench: Modifying Contexts for Targeted Latent Activation
2025
Cited
0
Resume (English only)
Background
Alignment Research Engineer
Co-authors
10 total
Neel Nanda
Mechanistic Interpretability Team Lead, Google DeepMind
David Chanin
University College London
Arthur Conmy
Google DeepMind
Curt Tigges
Science Lead, Decode Research
Robert Krzyzanowski
Poseidon Research
Co-author 6
Adam Karvonen
ML Researcher
Kola Ayonrinde
UK AI Safety Institute
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up