OhhMoo commited on
Commit
b9ce331
·
verified ·
1 Parent(s): e38ee69

explain what each chain tests and the three-chain design logic

Browse files
Files changed (1) hide show
  1. README.md +23 -0
README.md CHANGED
@@ -1,3 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # SAE × RL: Qwen2.5-0.5B on GSM8k (multi-condition)
2
 
3
  Warm-start TopK SAEs trained on residual-stream activations of
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: pytorch
4
+ language:
5
+ - en
6
+ pipeline_tag: feature-extraction
7
+ base_model: Qwen/Qwen2.5-0.5B-Instruct
8
+ datasets:
9
+ - openai/gsm8k
10
+ tags:
11
+ - sparse-autoencoder
12
+ - sae
13
+ - topk-sae
14
+ - interpretability
15
+ - mechanistic-interpretability
16
+ - ppo
17
+ - rlhf
18
+ - reasoning
19
+ - training-dynamics
20
+ - qwen
21
+ - qwen2.5
22
+ ---
23
+
24
  # SAE × RL: Qwen2.5-0.5B on GSM8k (multi-condition)
25
 
26
  Warm-start TopK SAEs trained on residual-stream activations of