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

Edit

-0.90

Ãī

-0.80

ALT

-0.77

Ò

-0.76

CI

-0.75

Allow

-0.75

Ã©r

-0.74

BU

-0.73

Joined

-0.73

Art

-0.72

POSITIVE LOGITS

 whole

1.05

 resultant

1.01

rouse

0.98

 heaviest

0.96

 typical

0.95

 combination

0.93

 mammoth

0.93

 result

0.92

new

0.91

 strongest

0.89

Activations Density 0.000%

No Known Activations

This feature has no known activations.