© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
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
GPT2-SMALL · 8-RES-JB · 15145 ｜ Neuronpedia
Home
Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
GPT2-Small
Residual Stream
8-RES-JB
15145
Prev
Next
MODEL
8-res-jb
Source/SAE
INDEX
Go
Explanations
words related to work and employment, particularly after taking time off
oai_token-act-pair · gpt-3.5-turbo
No Scores
variations of the word "let."
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
Avg Score: 55
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 8-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
8
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/8-res-jb/15145?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/8-res-jb/15145?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
swast
-0.72
Codec
-0.66
decomp
-0.66
bed
-0.64
photoc
-0.64
ZIP
-0.63
WM
-0.63
Guatem
-0.62
Bung
-0.62
mattress
-0.62
POSITIVE LOGITS
İ
1.05
¼
1.04
¬
1.04
£
1.01
ĸ
1.01
º
1.00
¾
0.99
eal
0.97
Ĭ
0.96
Ķ
0.95
Act
ivations
Density 0.275%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
