Skip to content
mini-lab
Features of prelude-2

Feature #281

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

Fires on
0.12% of tokens
Mostly in
chat
Layer
after block 4

Where it fires

  • chat 38%
  • agent 34%
  • story 27%
  • worksheet 1%
  • python 0%

Makes the model say

strong workingning themreplaceAll liked jobreat

Makes it not say

?" idea pnew oldp!" into

Strongest examples

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

  1. chat 2.5
    Hi!<|user_end|><|assistant_start|>Hi there! Would you like a story,
  2. story 2.24
    oey, I want to examine something with you. Would you help me?" Joe
  3. chat 2.23
    5.<|assistant_end|><|user_start|>hey there<|user_end|><|assistant_start|>Hi there! Would you like a story,
  4. story 2.21
    butterfly! I'm so happy you came to see me. Would you like to go down
  5. story 2.13
    my toys. I have dolls, cars, and blocks. Would you like to help me
  6. chat 2.11
    !".<|system_end|><|user_start|>Hi<|user_end|><|assistant_start|>Sure! Hi there! Would you like a story,
  7. story 2.1
    ffball said, "My name is Poke. Would you like to be friends
  8. chat 2.07
    .<|assistant_end|><|bos|><|user_start|>Good morning!<|user_end|><|assistant_start|>Hi there! Would you like a story,
  9. chat 2.05
    !".<|system_end|><|user_start|>Hi<|user_end|><|assistant_start|>Sure! Hi there! Would you like a story,
  10. story 2.04
    you, Thomas. I'm Millie. Would you like to help me
  11. chat 2.03
    <|system_end|><|user_start|>Hi!<|user_end|><|assistant_start|>Sure! Hi there! Would you like a story,
  12. chat 1.98
    !".<|system_end|><|user_start|>Hi<|user_end|><|assistant_start|>Sure! Hi there! Would you like a story,