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
27384
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
instances of the word "featuring."
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/27384?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/27384?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
+0.27
1.6%
156
+0.16
0.9%
23
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
443
+0.27
0.01
306
+0.16
0.01
46
+0.14
0.01
Negative Logits
ian
-1.70
orer
-1.56
si
-1.50
shire
-1.46
idopsis
-1.46
abel
-1.45
ierno
-1.44
doi
-1.42
lew
-1.42
ardi
-1.40
POSITIVE LOGITS
Ļ
2.39
Ĥ
2.09
ł
2.08
¢
2.08
¬
2.06
³
1.99
Ģ
1.99
Ķ
1.98
¤
1.98
ľĵ
1.93
Act
ivations
Density 0.282%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
