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 1536
8-RES_FS1536-JB
424
Prev
Next
MODEL
8-res_fs1536-jb
Source/SAE
INDEX
Go
Explanations
terms related to legal documents and criminal activities
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 8-res_fs1536-jb
Configuration
jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
1,536
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_fs1536-jb/424?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_fs1536-jb/424?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
218
+0.12
0.5%
238
+0.10
0.5%
249
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
288
+0.12
0.18
575
+0.10
0.15
225
+0.10
0.12
Negative Logits
NOR
-0.53
ELL
-0.46
ulus
-0.46
noon
-0.46
Rim
-0.45
abad
-0.45
cell
-0.45
mum
-0.44
din
-0.44
peas
-0.43
POSITIVE LOGITS
thereof
1.68
of
1.58
of
1.30
Of
1.27
Of
1.24
OF
1.16
oft
0.98
OF
0.93
luster
0.92
ghai
0.80
Act
ivations
Density 4.137%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
