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
Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
GPT2-Small
Residual Stream
11-RES-JB
10628
Prev
Next
MODEL
11-res-jb
Source/SAE
INDEX
Go
Explanations
various forms of the phrase "You're welcome."
oai_token-act-pair · gpt-3.5-turbo
No Scores
the representation of a welcoming or inclusive atmosphere
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
Comparing With
GPT2-SMALL @ 11-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
24,576
Data Type
torch.float32
Hook Point
blocks.11.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
11
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/11-res-jb/10628?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/11-res-jb/10628?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
ãĥ¼ãĥĨ
-0.76
çīĪ
-0.69
Afric
-0.68
Sic
-0.67
Tid
-0.65
åĭ
-0.65
secretaries
-0.62
Sigma
-0.62
airs
-0.61
enegger
-0.61
POSITIVE LOGITS
¿
1.16
ª
1.11
«
1.06
¼
1.03
Ķ
1.00
į
0.98
¡
0.98
¹
0.96
¤
0.92
½
0.92
Act
ivations
Density 0.145%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
