INDEX

Explanations

references to the term "Ax" or variations of it

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

atters

-0.60

FORMATION

-0.59

urrent

-0.59

ĨĴ

-0.58

 Sparkle

-0.58

lights

-0.58

 transitioned

-0.58

ourage

-0.58

CLASSIFIED

-0.57

 Columb

-0.57

POSITIVE LOGITS

iom

1.41

illary

1.17

iop

0.96

xon

0.85

ansas

0.83

isy

0.82

yers

0.82

alon

0.81

ax

0.80

ios

0.79

Activations Density 0.033%

references to the term "Ax" or variations of it

No Comments

No Known Activations