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 768
8-RES_FS768-JB
515
Prev
Next
MODEL
8-res_fs768-jb
Source/SAE
INDEX
Go
Explanations
height measurements and location details
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_fs768-jb
Configuration
jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
768
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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gpt2-small/8-res_fs768-jb/515?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/8-res_fs768-jb/515?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
425
+0.12
0.6%
177
+0.11
0.5%
686
+0.11
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
425
+0.12
0.11
717
+0.11
0.09
711
+0.11
0.05
Negative Logits
Ĥª
-0.70
©¶æ¥µ
-0.67
ŃĶ
-0.59
?????-
-0.58
yssey
-0.54
wonders
-0.53
"!
-0.52
LET
-0.52
¬¼
-0.51
@#
-0.51
POSITIVE LOGITS
and
1.08
versus
1.01
nor
0.94
AND
0.90
or
0.87
vs
0.81
and
0.71
&
0.70
et
0.68
vs
0.60
Act
ivations
Density 6.036%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
