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
8627
Prev
Next
MODEL
11-res-jb
Source/SAE
INDEX
Go
Explanations
phrases that are repeated or emphasized in the text
oai_token-act-pair · gpt-3.5-turbo
No Scores
recurring phrases and concepts related to time and continuity
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 @ 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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gpt2-small/11-res-jb/8627?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/11-res-jb/8627?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
ibur
-0.52
onite
-0.52
mber
-0.47
imer
-0.45
IENT
-0.45
GER
-0.45
Sharp
-0.44
uted
-0.44
«
-0.44
Materials
-0.44
POSITIVE LOGITS
&
1.41
and
1.20
&
1.11
AND
1.07
and
1.00
/
0.94
or
0.91
/
0.90
etc
0.89
ands
0.89
Act
ivations
Density 0.866%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations