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

eus

-0.71

 purse

-0.69

apult

-0.68

emo

-0.66

ulhu

-0.63

['

-0.63

ulet

-0.63

cius

-0.62

izard

-0.62

gag

-0.61

POSITIVE LOGITS

Ĥª

0.79

addons

0.76

natureconservancy

0.74

sites

0.66

é¾

0.63

Ö

0.62

 Heights

0.61

crazy

0.60

fficiency

0.59

 Heath

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.