Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Feature Splitting for GPT2-Small
GPT2-Small
Residual Feature Splitting 3072
8-RES_FS3072-JB
1727
Prev
Next
MODEL
8-res_fs3072-jb
Source/SAE
INDEX
Go
Explanations
phrases related to political news and activities
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 8-res_fs3072-jb
Configuration
jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
3,072
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_fs3072-jb/1727?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_fs3072-jb/1727?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
87
+0.17
0.9%
264
+0.10
0.5%
680
+0.10
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
711
+0.17
0.04
87
+0.10
-0.11
264
+0.10
0.05
Negative Logits
.<
-0.69
.:
-0.69
!!!!!
-0.63
.",
-0.62
%.
-0.60
"!
-0.60
.(
-0.59
.,"
-0.58
unless
-0.57
."
-0.57
POSITIVE LOGITS
*)
0.96
})
0.90
)}
0.87
)]
0.86
?)
0.82
)]
0.81
?)
0.81
)\
0.75
?),
0.75
+)
0.73
Act
ivations
Density 6.479%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
