Skip to content
mini-lab
Features of prelude-2

Feature #2301

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

Fires on
0.38% of tokens
Mostly in
chat
Layer
after block 4

Where it fires

  • chat 62%
  • agent 16%
  • story 15%
  • worksheet 8%
  • python 1%

Makes the model say

doing tell mean two need window, do

Makes it not say

was fell The]doubledmin wasn `

Strongest examples

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

  1. chat 5.66
    <|user_start|>What are you good at?<|user_end|>
  2. chat 5.63
    <|bos|><|user_start|>What are you good at?<|user_end|>
  3. chat 5.63
    <|bos|><|user_start|>What are you good at?<|user_end|>
  4. chat 5.38
    7<|think_end|>The answer is 17.<|assistant_end|><|bos|><|user_start|>What are you good at?<|user_end|>
  5. agent 5.24
    running in OpenCode, a coding agent harness.<|system_end|><|user_start|>"What are you able to do?"
  6. chat 5.19
    47 + 25 = 72<|bos|><|user_start|>What are you good at?<|user_end|>
  7. chat 5.08
    answer is 15.<|assistant_end|><|user_start|>what are you good at<|user_end|><|assistant_start|>
  8. story 5.06
    walked up to him.⏎"Hey there son. What are you doing?"⏎B
  9. chat 5.04
    story soon.<|assistant_end|><|user_start|>What are you good at?<|user_end|>
  10. chat 5.03
    <|assistant_start|>The answer is 630.<|assistant_end|><|bos|><|user_start|>What are you good at?<|user_end|>
  11. agent 5.03
    return -x`. The tests pass now.<|assistant_end|><|user_start|>"What are you?"<|user_end|><|assistant_start|>I
  12. chat 5.02
    <|think_end|>The answer is 816.<|assistant_end|><|bos|><|user_start|>What are you good at?<|user_end|>