INDEX

Explanations

the word 'you' with varying degrees of emphasis or context

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

entimes

-0.79

ĸļ

-0.78

¿½

-0.76

ĺħ

-0.71

Ĥª

-0.70

GMT

-0.70

inction

-0.68

ģ«

-0.68

eca

-0.67

enges

-0.67

POSITIVE LOGITS

 guys

1.46

're

1.22

 yourselves

1.13

tub

1.06

sir

0.93

 gentlemen

0.92

've

0.88

'll

0.88

 filthy

0.86

 mileage

0.84

Activations Density 0.206%

the word 'you' with varying degrees of emphasis or context

No Comments

No Known Activations