goodfire-maxsloef commited on
Commit
a75e0db
·
verified ·
1 Parent(s): 54fb8bf

note logic sae fix

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -32,3 +32,5 @@ used [OpenR1-Math](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k), a
32
  large dataset for mathematical reasoning. These datasets allow us to discover
33
  the features that R1 uses to answer challenging problems that exercise its
34
  reasoning chops.
 
 
 
32
  large dataset for mathematical reasoning. These datasets allow us to discover
33
  the features that R1 uses to answer challenging problems that exercise its
34
  reasoning chops.
35
+
36
+ Note: the original uploaded version of the logic SAE was incorrect; the correct version was uploaded on 4/17. If you have any difficulty running the SAEs, please reach out to us!