Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
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
11918
Prev
Next
MODEL
10-res-jb
Source/SAE
INDEX
Go
Explanations
business or organization names
oai_token-act-pair · gpt-3.5-turbo
No Scores
proper nouns or the names of specific entities
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 @ 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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gpt2-small/10-res-jb/11918?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/10-res-jb/11918?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
Cody
-0.86
Lois
-0.85
GS
-0.84
Wit
-0.83
Meier
-0.80
gre
-0.79
Gret
-0.79
GS
-0.78
Williams
-0.77
Lei
-0.77
POSITIVE LOGITS
ab
1.50
AB
1.41
Ab
1.30
abs
1.28
aba
1.28
AB
1.28
abb
1.24
Ab
1.22
abo
1.21
Sab
1.12
Act
ivations
Density 0.310%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
