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
27580
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
keywords related to serious situations or threats
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/27580?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/27580?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
+0.30
1.8%
376
+0.18
1.1%
270
+0.13
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
270
+0.30
0.04
327
+0.18
0.03
386
+0.13
0.02
Negative Logits
orth
-1.59
agles
-1.52
present
-1.44
shore
-1.40
ries
-1.39
uras
-1.39
erm
-1.38
rique
-1.37
http
-1.35
bras
-1.34
POSITIVE LOGITS
ĻĤ
3.27
Īĺ
2.92
²
2.91
ľĵ
2.81
¾
2.75
»¿
2.74
ģ
2.74
·
2.66
ĩ
2.65
Ń
2.63
Act
ivations
Density 1.385%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
