Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog/Podcast
NEW
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/Podcast
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Feature Splitting for GPT2-Small
GPT2-Small
Residual Feature Splitting 6144
8-RES_FS6144-JB
5545
Prev
Next
MODEL
8-res_fs6144-jb
Source/SAE
INDEX
Go
Explanations
sports-related terms and statistics
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_fs6144-jb
Configuration
jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
6,144
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_fs6144-jb/5545?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_fs6144-jb/5545?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
564
+0.11
0.5%
166
+0.10
0.5%
575
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
39
+0.11
0.06
564
+0.10
0.06
575
+0.10
0.07
Negative Logits
Tes
-0.68
princ
-0.62
phys
-0.60
Tah
-0.58
Tes
-0.57
¡
-0.57
rall
-0.56
Suarez
-0.54
Kemp
-0.54
Zam
-0.54
POSITIVE LOGITS
.:
0.88
.(
0.85
.
0.85
.''.
0.84
.$
0.79
:,
0.78
.–
0.77
.#
0.77
.,
0.77
.--
0.76
Act
ivations
Density 0.830%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
