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
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
MLP Post
0-MLP-SM
27400
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
instances of the word "reading."
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/27400?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/27400?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
376
+0.13
0.7%
169
+0.12
0.7%
162
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
169
+0.13
0.01
503
+0.12
0.01
174
+0.12
0.01
Negative Logits
ī
-2.59
ı
-2.43
¦
-2.37
Ł
-2.33
ľ
-2.33
ĭ
-2.29
¨
-2.29
ĥ½
-2.29
ĺ
-2.27
¤
-2.24
POSITIVE LOGITS
ist
2.13
bank
1.97
ists
1.96
istic
1.88
aid
1.83
aids
1.62
grade
1.60
assistance
1.60
ibly
1.58
Aid
1.56
Act
ivations
Density 0.022%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
