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

anty

-0.78

gor

-0.75

utic

-0.73

auna

-0.72

erick

-0.71

andan

-0.71

spe

-0.69

anan

-0.69

ava

-0.68

gencies

-0.68

POSITIVE LOGITS

 Weather

0.62

acc

0.62

 Golf

0.60

 dstg

0.59

Works

0.58

World

0.58

WTC

0.56

 Transition

0.56

 divest

0.55

 Arnold

0.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.