Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Blog
Slack
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
8731
Prev
Next
MODEL
10-res-jb
Source/SAE
INDEX
Go
Explanations
words related to mandates or policies that are one-size-fits-all
oai_token-act-pair · gpt-3.5-turbo
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/8731?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/8731?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
to
-0.60
%%
-0.59
diction
-0.55
Nanto
-0.55
paper
-0.54
the
-0.52
tot
-0.51
IQ
-0.50
Wikipedia
-0.50
ped
-0.50
POSITIVE LOGITS
0.78
č
0.78
À
0.78
rawdownload
0.77
ü
0.77
Ă
0.77
ę
0.77
ė
0.77
ć
0.77
Ě
0.77
Act
ivations
Density 0.687%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
