Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Open Concept Steering
|
2 |
|
3 |
Open Concept Steering is an open-source library for discovering and manipulating interpretable features in large language models using Sparse Autoencoders (SAEs). Inspired by Anthropic's work on [Scaling Monosemanticity](https://transformer-circuits.pub/2024/scaling-monosemanticity/) and [Golden Gate Claude](https://www.anthropic.com/news/golden-gate-claude), this project aims to make concept steering accessible to the broader research community.
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
title: Open Concept Steering
|
4 |
+
sdk: static
|
5 |
+
emoji: 👁
|
6 |
+
colorFrom: indigo
|
7 |
+
colorTo: indigo
|
8 |
+
short_description: Training SAEs
|
9 |
+
---
|
10 |
# Open Concept Steering
|
11 |
|
12 |
Open Concept Steering is an open-source library for discovering and manipulating interpretable features in large language models using Sparse Autoencoders (SAEs). Inspired by Anthropic's work on [Scaling Monosemanticity](https://transformer-circuits.pub/2024/scaling-monosemanticity/) and [Golden Gate Claude](https://www.anthropic.com/news/golden-gate-claude), this project aims to make concept steering accessible to the broader research community.
|