LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

HTML

SAELens

Training Sparse Autoencoders on Language Models

HTMLEmerging

Stars

—

Forks

—

Contributors

8

Last push

26mo ago

Recent commits

Latest commits.

Fix: sparsity norm calculated at incorrect dimension. (#119)
ce95fb2Fengyuan Hu26mo ago
1.3.0
36919e0github-actions26mo ago
fix: replace list_files_info with list_repo_tree (#117)
676062cDavid Chanin26mo ago
fix: Improved activation initialization, fix using argument to pass in API key (#116)
7047bccjohnny26mo ago
feat: add activation bins for neuronpedia outputs, and allow customizing quantiles (#113)
05d650djohnny26mo ago

feat: Update for Neuropedia auto-interp (#112)

033283djohnny26mo ago

feat: SparseAutoencoder.from_pretrained() similar to transformer lens (#111)

617d416David Chanin26mo ago

1fda458github-actions26mo ago

Top contributors

Builders behind this project.