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
Residuals
1-RES-SM
26953
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
terms related to emotional or physical suffering
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__res-sm_processed/1-res-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.1.hook_resid_post
Hook Layer
1
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/1-res-sm/26953?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/1-res-sm/26953?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
125
+0.17
1.0%
334
+0.14
0.8%
474
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
125
+0.17
0.02
474
+0.14
0.03
334
+0.14
0.02
Negative Logits
Ń
-3.28
ĥ½
-3.08
Īĺ
-3.03
Ħ
-2.96
Ģ
-2.94
µ
-2.91
¬
-2.91
IJ
-2.89
¤
-2.87
čč
-2.77
POSITIVE LOGITS
here
1.62
from
1.53
yl
1.51
lord
1.51
worse
1.43
river
1.43
ant
1.40
curvature
1.39
nowadays
1.39
=>
1.38
Act
ivations
Density 0.103%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
