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
11-RES-JB
3000
Prev
Next
MODEL
11-res-jb
Source/SAE
INDEX
Go
Explanations
references to locations or entities involving the United States
oai_token-act-pair · gpt-3.5-turbo
No Scores
references to international conflicts and geopolitical issues
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 @ 11-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
11
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/11-res-jb/3000?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/11-res-jb/3000?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
---
-1.11
---
-0.98
—
-0.98
âĶĢâĶĢâĶĢâĶĢ
-0.88
—
-0.87
—"
-0.87
.--
-0.81
glim
-0.81
.—
-0.79
—-
-0.75
POSITIVE LOGITS
US
2.49
US
1.84
Nato
1.82
Nasa
1.74
UK
1.38
USA
1.30
(£
1.18
USAF
1.17
Pentagon
1.13
NZ
1.13
Act
ivations
Density 0.508%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
