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
10-RES-JB
11818
Prev
Next
MODEL
10-res-jb
Source/SAE
INDEX
Go
Explanations
captions or headings in articles
oai_token-act-pair · gpt-3.5-turbo
No Scores
text formatting indicators and structural elements
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 10-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
10
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/10-res-jb/11818?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/10-res-jb/11818?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
112
-0.70
82
-0.67
112
-0.64
78
-0.63
ERC
-0.62
1932
-0.62
222
-0.61
138
-0.61
138
-0.60
132
-0.60
POSITIVE LOGITS
5
1.34
5
1.24
Fif
0.97
five
0.92
fifth
0.90
fifth
0.90
525
0.87
ķ
0.85
505
0.85
525
0.84
Act
ivations
Density 0.065%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
