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
27304
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
specific phrases indicating locations or contexts
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
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/27304?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/27304?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
441
+0.13
0.7%
316
+0.11
0.7%
364
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
441
+0.13
0.08
316
+0.11
0.06
170
+0.11
0.06
Negative Logits
cheon
-1.54
neck
-1.49
amble
-1.44
SEC
-1.41
oplasma
-1.38
iplex
-1.37
]):
-1.36
icorn
-1.34
uber
-1.33
ouin
-1.31
POSITIVE LOGITS
ı
3.63
Ĩ
3.44
ĥ½
3.43
Ļ
3.41
Ģ
3.40
¹
3.28
¾
3.24
¤
3.16
ħ
3.15
İ
3.10
Act
ivations
Density 0.056%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
