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
2426
Prev
Next
MODEL
6
INDEX
Go
Explanations
of
No Scores
phrases about replacement, such as "take the place of" or similar
No Scores
place of or place to
No Scores
the word after "place" in expressions using the word "place", e.g. "take the place of" or "give place to"
No Scores
words indicating relationships, connections, and numerical values.
oai_token-act-pair · gpt-4-turbo
No Scores
Describing unfavorable substitutions that have happened
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/6/2426?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6/2426?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
