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
Dunefsky · Chlenski · Transcoders Enable Fine-Grained Interpretable Circuit Analysis
GPT2-Small
Transcoders Residuals
8-TRES-DC
6
Prev
Next
MODEL
8-tres-dc
Source/SAE
INDEX
Go
Explanations
references to images and media in digital content
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
Text inside square brackets
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/8-tres-dc/6?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/6?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
"))
-0.73
))
-0.70
.)
-0.69
)))
-0.69
.")
-0.68
));
-0.66
).
-0.63
):
-0.63
");
-0.62
Carbuncle
-0.62
POSITIVE LOGITS
]
1.56
]'
1.45
?]
1.41
']
1.39
][
1.37
]}
1.31
],
1.29
:]
1.25
](
1.24
]]
1.23
Act
ivations
Density 0.142%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
