Can Rager

6 papers · 2024–2025 · 4 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad

Venues

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

Top co-authors

Samuel Marks (4) David Bau (3) Yeu-Tong Lau (2) Adam Karvonen (2) Arthur Conmy (2) Jannik Brinkmann (2) Aaron Mueller (2) Neel Nanda (1) Curt Tigges (1) Eoin Farrell (1)

Research topics

Artificial Intelligence (6) Core AI (6) Deep Learning (2) Machine Learning (2) Natural Language Processing (2) Core Methods (2) Resources & Methods (2) Architectures (1) Learning Types (1) Techniques (1)

Keywords

language model (2) feature disentanglement (2) sparse autoencoder (2) feature extraction (1) interpretability (1) model architecture (1) neural network optimization (1) foundation model (1) attention head (1) language model interpretability (1) ground truth metric (1) circuit discovery (1) residual stream (1) model internal (1) memory management (1) activation patching (1) large language model (1) neural network (1) board game (1) feature ablation (1)

Papers

NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals ICLR 2025 SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability ICML 2025 Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models ICLR 2025 An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L EMNLP 2024 Attribution Patching Outperforms Automated Circuit Discovery EMNLP 2024 Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models NeurIPS 2024