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
15956
Prev
Next
MODEL
8-res-jb
Source/SAE
INDEX
Go
Explanations
Japanese characters that may not be relevant to the task at hand
oai_token-act-pair · gpt-3.5-turbo
No Scores
references to numerical values and identifiers related to events or data
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
Avg Score: 80
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/15956?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/15956?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
istant
-0.83
Synd
-0.82
ét
-0.81
Nat
-0.79
Nat
-0.78
Syndicate
-0.77
Canad
-0.76
Nost
-0.76
Resp
-0.76
NXT
-0.73
POSITIVE LOGITS
6
1.24
6
1.19
06
0.96
06
0.95
six
0.90
666
0.89
Sixth
0.86
Six
0.85
six
0.84
ole
0.83
Act
ivations
Density 0.199%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations