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
26754
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
indicators of a specific entity or brand
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/26754?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/26754?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
369
+0.25
1.4%
470
+0.14
0.8%
477
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
59
+0.25
0.02
369
+0.14
0.02
477
+0.14
0.03
Negative Logits
¿½
-2.38
ķ
-2.24
ľĵ
-2.17
¥
-2.11
ħ
-2.08
ĭ
-2.07
£
-2.03
ĵ
-2.02
ł
-2.01
ĩ
-1.96
POSITIVE LOGITS
akespeare
2.11
baz
1.73
apiro
1.70
rooms
1.69
cock
1.61
outs
1.51
room
1.49
Bengal
1.39
iah
1.37
war
1.36
Act
ivations
Density 0.056%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
