Skip to content
mini-lab
Features of prelude-2

Feature #1884

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

Fires on
0.58% of tokens
Mostly in
agent
Layer
after block 4

Where it fires

  • agent 85%
  • python 8%
  • story 4%
  • chat 3%
  • worksheet 0%

Makes the model say

ne table sunmy.'s danced eat

Makes it not say

out told2 about onlyoldStringdivOUNT

Strongest examples

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

  1. agent 3.18
    the average of a and b.<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=utils.py<|tool_call_end|><|assistant_end|>
  2. agent 2.89
    the smaller of a and b"<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=utils.py<|tool_call_end|><|assistant_end|>
  3. agent 2.86
    the number of characters in s.<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=strings.py<|tool_call_end|><|assistant_end|>
  4. agent 2.86
    doubles every number in nums.<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=utils.py<|tool_call_end|><|assistant_end|>
  5. agent 2.85
    the smaller of a and b.<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=utils.py<|tool_call_end|><|assistant_end|>
  6. agent 2.84
    the first letter of s please"<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=utils.py<|tool_call_end|><|assistant_end|>
  7. agent 2.83
    the sum of the numbers in nums<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=utils.py<|tool_call_end|><|assistant_end|>
  8. agent 2.82
    : it returns a minus b<|user_end|><|assistant_start|><|tool_call_start|>write<|arg|>path=utils.py<|arg|>content
  9. agent 2.82
    It returns the average of nums.<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=lists.py<|tool_call_end|><|assistant_end|>
  10. agent 2.78
    returns every number of nums doubled.<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=utils.py<|tool_call_end|><|assistant_end|>
  11. agent 2.77
    What's in utils.py?<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=utils.py<|tool_call_end|><|assistant_end|>
  12. agent 2.75
    the average of a and b.<|user_end|><|assistant_start|><|tool_call_start|>read<|arg|>path=utils.py<|tool_call_end|><|assistant_end|>