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
11949
Prev
Next
MODEL
10-res-jb
Source/SAE
INDEX
Go
Explanations
words related to ownership and occupation of land or territory
oai_token-act-pair · gpt-3.5-turbo
No Scores
terms related to access and limitation within socio-economic contexts
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/11949?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/11949?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
}}}
-0.78
Cheong
-0.62
;}
-0.62
]=
-0.62
wd
-0.61
Ô
-0.61
})
-0.61
};
-0.60
},
-0.59
)]
-0.59
POSITIVE LOGITS
that
1.40
that
1.32
THAT
1.06
That
0.86
That
0.81
thats
0.71
whereby
0.68
ito
0.63
rained
0.61
addock
0.61
Act
ivations
Density 0.587%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
