Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
GPT2-Small
6
2894
Prev
Next
MODEL
6
INDEX
Go
Explanations
the token '1st' specially in spell tables from tabletop RPG games
Explanation Uploaded by User
No Scores
The first of something
Explanation Uploaded by User
No Scores
ranking first
Explanation Uploaded by User
No Scores
numbers and related abbreviations.
oai_token-act-pair · gpt-4-turbo
No Scores
Rank
Explanation Uploaded by User
No Scores
highest
Explanation Uploaded by User
No Scores
tables of data, especially the first in the table
Explanation Uploaded by User
No Scores
very best
Explanation Uploaded by User
No Scores
best
Explanation Uploaded by User
No Scores
quantitative
Explanation Uploaded by User
No Scores
highest scoring
Explanation Uploaded by User
No Scores
Raw information and statements, especially in the context of games or competitions
Explanation Uploaded by User
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/6/2894?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6/2894?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