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
27473
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
references to legal cases and judicial citations
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/27473?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/27473?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
327
+0.16
0.9%
307
+0.12
0.7%
492
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
307
+0.16
0.04
327
+0.12
0.03
445
+0.12
0.03
Negative Logits
uego
-1.56
ear
-1.53
erce
-1.47
whom
-1.46
eligible
-1.45
ect
-1.45
orie
-1.40
eps
-1.39
ves
-1.36
Writers
-1.36
POSITIVE LOGITS
©
4.00
¦
3.75
¬
3.65
º
3.61
Ļª
3.58
ĭ
3.56
Į
3.52
«
3.50
ł
3.50
¶
3.48
Act
ivations
Density 0.034%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
