Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
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
9-RES-JB
12414
Prev
Next
MODEL
9-res-jb
Source/SAE
INDEX
Go
Explanations
the word stem "in" followed by an apostrophe and another word
oai_token-act-pair · gpt-3.5-turbo
No Scores
phrases and terms related to musical performances or movements
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 @ 9-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
9
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/9-res-jb/12414?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/9-res-jb/12414?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
ADRA
-0.86
ħ
-0.81
ynski
-0.75
ISC
-0.73
inct
-0.72
adra
-0.72
Ͻ
-0.70
auri
-0.69
idium
-0.66
pse
-0.65
POSITIVE LOGITS
'?
1.10
'
1.09
',"
1.07
'-
1.05
tha
1.01
'.
0.99
',
0.99
'."
0.97
':
0.97
'"
0.92
Act
ivations
Density 0.111%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations