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
26920
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
occurrences of the verb "examine" and its variations in the context of research or analysis
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/26920?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/26920?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
+0.30
1.8%
156
+0.21
1.2%
148
+0.17
1.0%
Correlated Neurons
Index
P. Corr.
Cos Sim.
148
+0.30
0.02
115
+0.21
0.01
45
+0.17
0.01
Negative Logits
IJ
-2.27
ŀ
-2.09
Ħ
-2.01
Ľ
-1.98
Ĵ
-1.95
§
-1.77
ĸ
-1.76
Ģ
-1.74
ĭ
-1.71
ī
-1.68
POSITIVE LOGITS
them
1.93
iqu
1.74
them
1.62
itely
1.54
ifferences
1.46
the
1.45
ivities
1.44
findings
1.44
how
1.43
idine
1.43
Act
ivations
Density 0.076%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
