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
8-RES-JB
16278
Prev
Next
MODEL
8-res-jb
Source/SAE
INDEX
Go
Explanations
numeric values in a specific range
oai_token-act-pair · gpt-3.5-turbo
No Scores
specific proper nouns, particularly names and locations
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
Avg Score: 66
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 8-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
8
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/8-res-jb/16278?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/8-res-jb/16278?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
creen
-0.84
hearts
-0.70
thin
-0.70
fair
-0.70
pher
-0.69
tten
-0.68
kens
-0.68
ms
-0.67
cock
-0.66
thin
-0.66
POSITIVE LOGITS
Ģ
1.40
ģ
1.40
į
1.30
ī
1.27
ĭ
1.25
ĩ
1.21
ĥ
1.20
Į
1.01
Ī
0.99
ij
0.99
Act
ivations
Density 0.020%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
