Scholar
Alex McKenzie
Google Scholar ID: HlFO1P4AAAAJ
AE Studio
AI Safety
AI Alignment
Mechanistic Interpretability
AI Safety Evaluations
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
3
H-index
1
i10-index
0
Publications
1
Co-authors
0
Contact
Email
hello@alexmck.com
GitHub
Open ↗
LinkedIn
Open ↗
Publications
4 items
Moral Preferences of LLMs Under Directed Contextual Influence
2026
Cited
0
Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs
2026
Cited
0
Endogenous Resistance to Activation Steering in Language Models
2026
Cited
0
Detecting High-Stakes Interactions with Activation Probes
2025
Cited
0
Resume (English only)
Research Experience
Working on AI Alignment at AE Studio.
Background
A researcher & software engineer who cares a lot about mitigating risks from Artificial Intelligence. Also interested in music, type systems, and Effective Altruism.
Miscellany
Often at the piano when not at work.
Co-authors
0 total
Co-authors: 0 (list not available)
×
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