Skip to content
mini-lab
Features of prelude-2

Feature #452

Fires on “ tree” (not labeled yet: read the examples)

Fires on
0.54% of tokens
Mostly in
story
Layer
after block 4

Where it fires

  • story 34%
  • worksheet 32%
  • chat 29%
  • agent 5%
  • python 0%

Makes the model say

9 now prelude and =ance1ue

Makes it not say

C( bigLab only hardly

Strongest examples

On text the dictionary never trained on. The underlined token is where it fires most.

  1. story 1.9
    under a big tree and shared the nuts
  2. story 1.88
    climbed to the top of a tall tree. He put on
  3. story 1.81
    text.py`, line 1.<|assistant_end|><|bos|>Once upon a time, a bald man named
  4. story 1.78
    to ten, and Ben and Max run to hide behind a big tree.⏎"Read
  5. story 1.77
    As Tim rode his bike, he saw a smelly cat stuck in a tree. "Don't
  6. story 1.76
    : `add(a, b)`.<|assistant_end|><|bos|>Once upon a time, there was a boy
  7. chat 1.74
    for a walk. The dog saw a small cat sitting under a tree.<|assistant_end|><|user_start|>Bye
  8. story 1.73
    rock friend.⏎Suddenly, Tim saw a small cat stuck in a tree. The cat was
  9. story 1.73
    is_divisible(a, b)`.<|assistant_end|><|bos|>Once upon a time, there was a big
  10. story 1.72
    <|assistant_start|>Created `greeting.py`.<|assistant_end|><|bos|>Once upon a time, there was a little
  11. story 1.72
    <|assistant_start|>Created `greeting.py`.<|assistant_end|><|bos|>Once upon a time, a little girl named
  12. story 1.71
    <|tool_end|><|assistant_start|>Created `hello.py`.<|assistant_end|><|bos|>Once upon a time, there was a girl