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
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
MLP Post
0-MLP-SM
27481
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
formatting indicators or placeholders in code or text
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
Configuration
ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
How To Load
Prompts (Dashboard)
32,768 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
32,768
Data Type
torch.float32
Hook Name
blocks.0.hook_mlp_out
Hook Layer
0
Architecture
standard
Context Size
128
Dataset
EleutherAI/the_pile_deduplicated
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/pythia-70m-deduped/0-mlp-sm/27481?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/0-mlp-sm/27481?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
0
+0.15
0.9%
115
+0.12
0.7%
16
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
0
+0.15
0.04
261
+0.12
0.03
390
+0.12
0.03
Negative Logits
©
-3.00
ľ
-2.74
Ń
-2.73
ı
-2.71
´
-2.70
º
-2.70
»
-2.70
ħ
-2.69
·
-2.67
¸
-2.66
POSITIVE LOGITS
umab
1.62
endi
1.56
chitz
1.53
iliar
1.51
laws
1.50
rpm
1.49
iani
1.48
!”
1.45
ylon
1.45
ureus
1.45
Act
ivations
Density 0.020%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
