Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 BlackboxNLP WS

Tom Lieberum | Senthooran Rajamanoharan | Arthur Conmy | Lewis Smith | Nicolas Sonnerat | Vikrant Varma | Janos Kramar | Anca Dragan | Rohin Shah | Neel Nanda |

Attribution Patching Outperforms Automated Circuit Discovery BlackboxNLP WS

Aaquib Syed | Can Rager | Arthur Conmy |

Copy Suppression: Comprehensively Understanding a Motif in Language Model Attention Heads BlackboxNLP WS

Callum Stuart McDougall | Arthur Conmy | Cody Rushing | Thomas McGrath | Neel Nanda |