INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 differential

-0.78

è£ħ

-0.67

 excavation

-0.64

 curved

-0.63

 captcha

-0.61

 deduct

-0.61

waukee

-0.61

 landfall

-0.60

 appendix

-0.59

 randomized

-0.59

POSITIVE LOGITS

eers

0.82

uine

0.82

erness

0.74

Leaks

0.73

Virgin

0.73

resso

0.72

cdn

0.71

ria

0.70

mint

0.70

onica

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.