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
26773
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
references to news agencies, particularly the Associated Press
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__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/26773?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/26773?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
443
+0.12
0.7%
410
+0.12
0.7%
101
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
111
+0.12
0.05
271
+0.12
0.02
156
+0.11
0.03
Negative Logits
ĥ½
-3.58
ľĵ
-3.18
ķ
-3.16
¸
-3.15
ĺ
-3.10
ĵ
-3.08
¶
-3.08
Ĥ
-3.06
ij
-2.99
Ł
-2.98
POSITIVE LOGITS
urized
2.34
edly
1.98
ful
1.95
docs
1.87
ressor
1.87
ive
1.84
fully
1.84
rente
1.83
esy
1.83
enthal
1.83
Act
ivations
Density 0.303%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
