Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog/Podcast
NEW
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/Podcast
GitHub
Slack
Twitter
Contact
Home
GPT2-Small
6
1307
Prev
Next
MODEL
6
INDEX
Go
Explanations
the word "surprising"
No Scores
words and phrases related to expectation and judgment.
oai_token-act-pair · gpt-4-turbo
No Scores
'surprising' in the context of things not being surprising
No Scores
the words 'surprising' and 'unexpected' after a negation
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/6/1307?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6/1307?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
