INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 compr

-0.76

ãĥ¢

-0.71

 blessing

-0.70

img

-0.63

 flowering

-0.63

 predecessor

-0.62

 fertility

-0.61

Brother

-0.61

 encour

-0.60

thy

-0.60

POSITIVE LOGITS

ateur

0.87

))))

0.83

doi

0.82

ctors

0.78

eros

0.77

erd

0.77

ukong

0.77

onde

0.75

mson

0.74

ijk

0.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.