Hugging Face's logo

pyvene
/
gemma-reft-2b-it-res

ReFT
Model card Files Community
1
zhengxuanzenwu commited on
Commit
d9e9b7a
·
verified ·
1 Parent(s): e885ea7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -6,6 +6,8 @@ tags:
6
 
7
  # 1. AxBench
8
 
 
 
9
  AxBench evaluates interpretability methods in terms of concept detection and model steering. AxBench releases two supervised dictionary learning methods that outperforms existing methods including SAEs. These dictionaries contain 1D subspaces that map to high-level concepts.
10
 
11
  # 2. What is `gemma-reft-2b-it-res`?
 
6
 
7
  # 1. AxBench
8
 
9
+ **Live Demo:** https://huggingface.co/spaces/pyvene/AxBench-ReFT-r1-16K
10
+
11
  AxBench evaluates interpretability methods in terms of concept detection and model steering. AxBench releases two supervised dictionary learning methods that outperforms existing methods including SAEs. These dictionaries contain 1D subspaces that map to high-level concepts.
12
 
13
  # 2. What is `gemma-reft-2b-it-res`?