Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog/Podcast
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/Podcast
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
GPT2-Small
Residual Stream
0-RES-JB
14234
Prev
Next
MODEL
0-res-jb
Source/SAE
INDEX
Go
Explanations
the name "Puig" with varying levels of association
oai_token-act-pair · gpt-3.5-turbo
No Scores
references to the term "Puig" or variations of it, likely connected to a specific context or individual
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 @ 0-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
0
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/0-res-jb/14234?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/0-res-jb/14234?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
amazon
-0.76
ARK
-0.75
cod
-0.73
Ark
-0.66
array
-0.63
corn
-0.63
egal
-0.62
cover
-0.61
ivable
-0.61
wire
-0.60
POSITIVE LOGITS
Pu
4.26
pu
2.29
pu
1.23
Fu
1.18
Fra
1.10
Guan
1.08
Cu
1.08
Fu
1.07
Vu
1.07
Cu
1.06
Act
ivations
Density 0.017%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations