Lewis Smith

4 papers · 2020–2024 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird

Venues

NeurIPS (2) EMNLP (1) ICML (1)

Top co-authors

Senthooran Rajamanoharan (2) Neel Nanda (2) Rohin Shah (2) Tom Lieberum (2) Vikrant Varma (2) Arthur Conmy (2) Yarin Gal (2) János Kramár (2) Nicolas Sonnerat (1) Sebastian Farquhar (1)

Research topics

Artificial Intelligence (4) Machine Learning (4) Deep Learning (3) Core AI (3) Architectures (2) Core Methods (2) Learning Types · Machine Learning (2) Bayesian & Probabilistic (1) Learning Types · Deep Learning (1) Optimization & Theory (1)

Keywords

sparse autoencoder (2) variational inference (1) uncertainty quantification (1) neural network interpretability (1) model analysis (1) deep learning (1) mean-field approximation (1) stochastic process (1) hamiltonian monte carlo (1) latent representation (1) language model (1) out-of-distribution detection (1) feature decomposition (1) bayesian neural network (1) deep ensemble (1) interpretable feature (1) gradient penalty (1) deterministic uncertainty quantification (1) rbf network (1) weight posterior (1)

Papers

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 EMNLP 2024 Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders NeurIPS 2024 Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations NeurIPS 2020 Uncertainty Estimation Using a Single Deep Deterministic Neural Network ICML 2020