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
8649
Prev
Next
MODEL
10-res-jb
Source/SAE
INDEX
Go
Explanations
numeric patterns and codes with special characters
oai_token-act-pair · gpt-3.5-turbo
No Scores
numerical data and statistics related to performance metrics
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/8649?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/8649?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
eighty
-0.68
seventy
-0.62
sixty
-0.61
æ°
-0.61
Sevent
-0.60
exha
-0.60
fifty
-0.59
ixty
-0.58
taining
-0.58
thirty
-0.57
POSITIVE LOGITS
3
1.82
2
1.80
4
1.66
1
1.62
5
1.42
3
1.36
2
1.31
6
1.27
4
1.20
7
1.17
Act
ivations
Density 0.206%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
