Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog
Slack
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
26996
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
references to government or political situations
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/26996?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/26996?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
23
+0.35
2.1%
478
+0.28
1.7%
410
+0.13
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
501
+0.35
0.04
410
+0.28
0.06
472
+0.13
0.05
Negative Logits
Ŀ
-2.56
Ħ
-2.42
Ļ
-2.38
ŀ
-2.34
®
-2.34
Ģ
-2.33
´
-2.30
¬
-2.29
ĻĤ
-2.29
»¿
-2.28
POSITIVE LOGITS
calm
2.01
slight
1.82
ASSERT
1.79
hypot
1.73
panic
1.73
abandon
1.72
blo
1.66
clear
1.62
an
1.61
little
1.60
Act
ivations
Density 0.658%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
