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
27300
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
phrases that emphasize the importance of accuracy
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/27300?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/27300?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
156
+0.21
1.2%
148
+0.15
0.9%
376
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
407
+0.21
0.02
79
+0.15
0.02
86
+0.14
0.02
Negative Logits
aker
-1.77
renn
-1.55
acker
-1.54
itian
-1.51
orian
-1.48
ori
-1.48
urer
-1.47
ker
-1.47
obacterium
-1.46
ussels
-1.45
POSITIVE LOGITS
ŀ
3.10
¥
3.02
ģ
2.99
¡
2.97
Ļ
2.88
«
2.79
ĻĤ
2.77
Ģ
2.75
µ
2.75
ļ
2.75
Act
ivations
Density 0.015%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
