INDEX

Explanations

phrases related to exceptional or unparalleled events

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

belt

-0.76

agra

-0.76

ather

-0.74

tops

-0.72

udder

-0.69

strings

-0.69

claimer

-0.68

uay

-0.67

guards

-0.67

ueller

-0.65

POSITIVE LOGITS

ly

0.97

LY

0.95

 proportions

0.87

 unanim

0.85

itarian

0.84

 amounts

0.82

 occurrence

0.82

 unprecedented

0.81

ITY

0.79

 lows

0.79

Activations Density 0.038%

phrases related to exceptional or unparalleled events

No Comments

No Known Activations