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

aughs

-0.70

adv

-0.69

hiba

-0.68

avers

-0.64

AAF

-0.63

onom

-0.63

aver

-0.62

arton

-0.61

hetically

-0.61

wit

-0.60

POSITIVE LOGITS

plane

0.74

Sop

0.71

 Secret

0.71

 Parenthood

0.66

strate

0.64

 artery

0.63

halla

0.62

Ra

0.62

 duties

0.61

path

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.