Scholar
Edward Stevinson
Google Scholar ID: m4_WK5oAAAAJ
Imperial College
Verification of Neural Networks
Mechanistic Interpretability
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
5
H-index
2
i10-index
0
Publications
5
Co-authors
0
Publications
6 items
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
2026
Cited
0
From Data Statistics to Feature Geometry: How Correlations Shape Superposition
2026
Cited
0
Adversarial Attacks Leverage Interference Between Features in Superposition
2025
Cited
0
ContextBench: Modifying Contexts for Targeted Latent Activation
2025
Cited
0
Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
2025
Cited
0
A Scalable Approach to Probabilistic Neuro-Symbolic Verification
2025
Cited
0
