Lev McKinney

University of Toronto

Lev McKinney worked as a Research Engineer at FAR.AI working on language model interpretability.

Publications

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution

Interpretability

Concept Influence attributes model behaviors to semantic directions (like linear probes or sparse autoencoder features) rather than individual test examples, improving identification of the training data that disproportionately drive unintended behaviors. Simple first-order approximations match or outperform standard influence functions while achieving over 20× computational speedups, though they degrade under significant distribution shifts.

February 18, 2026
Date Range

Eliciting Latent Predictions from Transformers with the Tuned Lens

Interpretability

The tuned lens learns an affine transformation to decode the activations of each layer of a transformer as next-token predictions. This provides insights into how model predictions are refined layer by layer. We validate our method on various autoregressive language models up to 20B parameters, showing it to be more predictive, reliable and unbiased than the logit lens baseline.

March 14, 2023
Date Range

News

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution

Interpretability

Concept Influence attributes model behaviors to semantic directions (like linear probes or sparse autoencoder features) rather than individual test examples, improving identification of the training data that disproportionately drive unintended behaviors. Simple first-order approximations match or outperform standard influence functions while achieving over 20× computational speedups, though they degrade under significant distribution shifts.

February 18, 2026
Date Range

Research

Our research explores a portfolio of high-potential agendas.

Events

Our events bring together global leaders in AI.

Programs

Our programs build the field of trustworthy and secure AI