Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
GPT2-Small
Residual Similar CE E2E Recon
6-RES_SCEFR-AJT
13917
Prev
Next
MODEL
6-res_scefr-ajt
Source/SAE
INDEX
Go
Explanations
computer-related instructions and technological terms
oai_token-act-pair · gpt-3.5-turbo
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
How To Load
Prompts (Dashboard)
12,288 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
46,080
Data Type
torch.float32
Hook Point
blocks.6.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
apollo-research/Skylion007-openwebtext-tokenizer-gpt2
Hook Point Layer
6
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/6-res_scefr-ajt/13917?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6-res_scefr-ajt/13917?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
199
+0.13
0.5%
151
+0.13
0.4%
127
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
199
+0.13
0.05
699
+0.13
0.03
127
+0.13
0.04
Negative Logits
ãģ®éŃĶ
-1.08
enburg
-1.07
Nanto
-1.04
enegger
-1.00
Amon
-0.91
iary
-0.90
JPEG
-0.86
Sidd
-0.86
Kag
-0.84
Amit
-0.83
POSITIVE LOGITS
¿
1.49
¨
1.44
³
1.43
´
1.42
¹
1.41
¦
1.37
¤
1.37
º
1.35
¸
1.34
¬
1.32
Act
ivations
Density 0.748%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
