INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

chu

-0.76

puted

-0.67

akes

-0.67

nant

-0.66

 Bravo

-0.65

 Tests

-0.63

inces

-0.60

Raw

-0.60

behind

-0.60

 Tags

-0.60

POSITIVE LOGITS

DragonMagazine

0.78

éŃĶ

0.74

nesota

0.71

aunder

0.71

Journal

0.70

orgetown

0.69

Magikarp

0.68

LIST

0.65

Â·Â·

0.65

ocity

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.