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
2-RES-JB
10681
Prev
Next
MODEL
2-res-jb
Source/SAE
INDEX
Go
Explanations
characters from a non-Latin alphabet
oai_token-act-pair · gpt-3.5-turbo
No Scores
special characters or symbols in the text
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 @ 2-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
2
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/2-res-jb/10681?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/2-res-jb/10681?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
icka
-0.87
ftime
-0.86
linger
-0.84
assemb
-0.81
nyder
-0.77
eson
-0.72
agre
-0.71
alys
-0.70
anol
-0.69
eele
-0.69
POSITIVE LOGITS
æĪ
1.45
æĹ
1.43
¥
1.40
åħ
1.38
İ
1.38
çĶ
1.36
³
1.35
´
1.35
ĥ
1.34
æ
1.34
Act
ivations
Density 0.013%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
