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
8-RES-JB
15965
Prev
Next
MODEL
8-res-jb
Source/SAE
INDEX
Go
Explanations
numbers and statistics in a format defined by a series of digits and descriptions
oai_token-act-pair · gpt-3.5-turbo
No Scores
numerical values and their significance in a statistical context
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
Avg Score: 91
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/8-res-jb/15965?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/8-res-jb/15965?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
aido
-0.75
BIP
-0.67
jah
-0.65
edient
-0.65
TPS
-0.65
idad
-0.65
agonist
-0.64
reb
-0.64
amaz
-0.64
UID
-0.64
POSITIVE LOGITS
34
0.80
31
0.77
41
0.77
37
0.76
00
0.75
50
0.75
66
0.75
75
0.75
68
0.74
38
0.73
Act
ivations
Density 0.146%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations