Scholar
Kola Ayonrinde
Google Scholar ID: j40ixccAAAAJ
UK AI Safety Institute
Mechanistic Interpretability
Philosophy of AI
Active Inference
AI Safety
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
73
H-index
4
i10-index
3
Publications
10
Co-authors
12
list available
Publications
6 items
RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
2026
Cited
0
From Mechanistic to Compositional Interpretability
2026
Cited
0
Auditing Games for Sandbagging
2025
Cited
0
Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii
2025
Cited
1
A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i
2025
Cited
0
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
2025
Cited
2
Co-authors
12 total
Adam Karvonen
ML Researcher
David Chanin
University College London
Johnny Lin
Neuronpedia
Arthur Conmy
Google DeepMind
Neel Nanda
Mechanistic Interpretability Team Lead, Google DeepMind
Michael T Pearce
Stanford University
Curt Tigges
Science Lead, Decode Research
Joseph Isaac Bloom
UK AI Safety Institute
