INDEX

Explanations

mentions of being physically located or situated at a specific place

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

formance

-0.75

selves

-0.72

aceutical

-0.70

vous

-0.68

PH

-0.66

manship

-0.65

iframe

-0.65

Ð¼

-0.64

gans

-0.63

alth

-0.63

POSITIVE LOGITS

 home

1.01

 least

0.97

onement

0.89

 logger

0.87

 liberty

0.81

 Disneyland

0.79

 Costco

0.77

 boarding

0.75

sea

0.74

 Hogwarts

0.74

Activations Density 0.150%

mentions of being physically located or situated at a specific place

No Comments

No Known Activations