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
12-RES-JB
14622
Prev
Next
MODEL
12-res-jb
Source/SAE
INDEX
Go
Explanations
keywords related to political or administrative issues
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
No Scores
expressions related to accountability and failure in public services
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 @ 12-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
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_post
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/12-res-jb/14622?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/12-res-jb/14622?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
.).
-1.04
.),
-1.03
.)
-0.97
.):
-0.91
?).
-0.87
,)
-0.80
?),
-0.79
.]
-0.76
.)
-0.68
!.
-0.68
POSITIVE LOGITS
"
2.26
%"
1.76
"-
1.72
"(
1.67
"[
1.65
"...
1.62
"'
1.61
"?
1.58
"â̦
1.54
''
1.52
Act
ivations
Density 0.781%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations