Neel Nanda
Mechanistic Interpretability Lead, Google DeepMind | Creator of TransformerLens
Verified Proof of Work Artifacts
2 items catalogedEach artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Neel Nanda. Every entry undergoes editorial source verification.
TransformerLens: Open Source Mechanistic Interpretability Framework
Created and maintains the premier open-source library allowing researchers to hook into, intervene upon, and cache intermediate activations across 50+ autoregressive transformer architectures with PyTorch integration.
Activation patching on models larger than 70B parameters requires substantial distributed multi-GPU memory.
Progress Measures for Grokking via Mechanistic Interpretability
Reverse-engineered the exact circular Fourier representation circuits formed when transformers 'grok' modular addition long after overfitting, proving that continuous generalization progresses silently before discontinuous performance jumps.
Toy model arithmetic circuits do not fully capture superposition and polysemanticity present in production-scale language models.