INDEX

Explanations

proper nouns referring to geographical locations

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

cember

-0.92

ynthesis

-0.75

merce

-0.74

onym

-0.73

bsite

-0.70

 VIDEOS

-0.66

 recip

-0.66

zinski

-0.65

vana

-0.65

ebook

-0.65

POSITIVE LOGITS

 Symphony

0.88

 Metropolitan

0.85

 Mutual

0.84

 natives

0.83

 Tourism

0.82

 University

0.80

 bureau

0.79

 businessman

0.78

Mov

0.76

 Public

0.76

Activations Density 0.327%

proper nouns referring to geographical locations

No Comments

No Known Activations