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 · Feature Splitting for GPT2-Small
GPT2-Small
Residual Feature Splitting 49152
8-RES_FS49152-JB
46035
Prev
Next
MODEL
8-res_fs49152-jb
Source/SAE
INDEX
Go
Explanations
words associated with commands and directives
oai_token-act-pair · gpt-4o-mini
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_fs49152-jb
Configuration
jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
49,152
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_fs49152-jb/46035?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_fs49152-jb/46035?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
387
+0.12
0.5%
98
+0.12
0.5%
696
+0.10
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
696
+0.12
0.02
227
+0.12
0.01
493
+0.10
0.01
Negative Logits
illi
-0.73
Feder
-0.67
ritic
-0.66
tten
-0.64
ici
-0.64
IFA
-0.64
Garry
-0.64
illian
-0.63
rito
-0.63
CAM
-0.63
POSITIVE LOGITS
up
1.66
ups
1.45
Up
1.43
up
1.36
UP
1.33
Up
1.31
ups
1.22
UP
1.15
upt
1.06
Ups
1.00
Act
ivations
Density 0.036%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
