János Kramár
Also published as: Janos Kramar
2024
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
Tom Lieberum
|
Senthooran Rajamanoharan
|
Arthur Conmy
|
Lewis Smith
|
Nicolas Sonnerat
|
Vikrant Varma
|
Janos Kramar
|
Anca Dragan
|
Rohin Shah
|
Neel Nanda
Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse decomposition of a neural network’s latent representations into seemingly interpretable features.Despite recent excitement about their potential, research applications outside of industry are limited by the high cost of training a comprehensive suite of SAEs.In this work, we introduce Gemma Scope, an open suite of JumpReLU SAEs trained on all layers and sub-layers of Gemma 2 2B and 9B and select layers of Gemma 2 27B base models.We primarily train SAEs on the Gemma 2 pre-trained models, but additionally release SAEs trained on instruction-tuned Gemma 2 9B for comparison.We evaluate the quality of each SAE on standard metrics and release these results.We hope that by releasing these SAE weights, we can help make more ambitious safety and interpretability research easier for the community. Weights and a tutorial can be found at https://huggingface.co/google/gemma-scope and an interactive demo can be found at https://neuronpedia.org/gemma-scope.
2010
A Generalized-Zero-Preserving Method for Compact Encoding of Concept Lattices
Matthew Skala
|
Victoria Krakovna
|
János Kramár
|
Gerald Penn
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Search
Co-authors
- Matthew Skala 1
- Victoria Krakovna 1
- Gerald Penn 1
- Tom Lieberum 1
- Senthooran Rajamanoharan 1
- show all...