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
MLP Post
0-MLP-SM
27623
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
references to constructors in programming contexts
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__mlp-sm_processed/0-mlp-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.0.hook_mlp_out
Hook Layer
0
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/0-mlp-sm/27623?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/0-mlp-sm/27623?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
376
+0.12
0.7%
8
+0.12
0.7%
162
+0.11
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
331
+0.12
0.01
57
+0.12
0.01
8
+0.11
0.01
Negative Logits
·
-3.57
ĥ
-3.35
§
-3.35
¿
-3.29
·¸
-3.28
Ī
-3.21
ĥ½
-3.20
į
-3.19
º
-3.15
²
-3.13
POSITIVE LOGITS
ality
1.90
idable
1.84
hower
1.76
raits
1.65
nell
1.63
ally
1.60
atted
1.59
isions
1.58
liga
1.57
fires
1.54
Act
ivations
Density 0.017%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
