INDEX

Explanations

words related to locations, especially focusing on the city of San Francisco

oai_token-act-pair · gpt-3.5-turbo

references to the city of San Francisco

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

•ans

#1 activation: 51.73

No Comments

Negative Logits

 Jinn

-0.66

 adjud

-0.61

 Neph

-0.59

 Avenger

-0.58

 Machina

-0.57

 Naval

-0.56

 Siren

-0.56

 Izan

-0.55

 expectancy

-0.55

weapons

-0.55

POSITIVE LOGITS

isco

1.15

ruary

0.83

furt

0.75

Ã§a

0.72

bees

0.72

å£«

0.68

rance

0.68

fur

0.66

ais

0.65

cest

0.65

Activations Density 0.047%

words related to locations, especially focusing on the city of San Francisco

references to the city of San Francisco

No Comments

No Known Activations