Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
146
Prev
Next
MODEL
8-tres-dc
INDEX
Go
Explanations
special characters or symbols that may indicate formatting or emphasis
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/8-tres-dc/146?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/8-tres-dc/146?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
hog
-0.70
comes
-0.58
stagn
-0.56
nick
-0.55
berus
-0.55
better
-0.54
ucker
-0.53
bull
-0.53
stay
-0.52
qv
-0.52
POSITIVE LOGITS
�
1.00
�
0.96
�
0.95
�
0.91
�
0.89
��
0.89
�
0.87
�
0.86
�
0.85
�
0.83
Act
ivations
Density 0.143%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
