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
26859
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
occurrences of the word "arrived" and its variations
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/26859?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/26859?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
115
+0.13
0.7%
156
+0.13
0.7%
72
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
72
+0.13
0.03
115
+0.13
0.02
46
+0.11
0.02
Negative Logits
ĥ½
-3.77
§
-3.47
ĭ
-3.12
©
-3.06
³
-3.03
Į
-3.02
ij
-2.97
Ń
-2.94
¶
-2.92
Ĥ¬
-2.91
POSITIVE LOGITS
atri
1.79
ents
1.64
ensibly
1.52
antic
1.51
ETHOD
1.50
at
1.49
aboard
1.48
enti
1.45
arriv
1.43
hof
1.41
Act
ivations
Density 0.182%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
