INDEX

Explanations

words related to measurements and quantities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'f'

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

Not in Any Lists

No Comments

Negative Logits

 Mori

-1.15

 Modi

-1.02

alore

-0.91

Nar

-0.89

Dur

-0.87

 Ferr

-0.86

dict

-0.84

 Godzilla

-0.83

DPR

-0.80

 crore

-0.80

POSITIVE LOGITS

 bird

1.39

 birds

1.39

 Birds

1.33

 poultry

1.33

 Bird

1.31

Bird

1.24

 chickens

1.23

Egg

1.22

 Eggs

1.21

 feathers

1.20

Activations Density 0.438%

words related to measurements and quantities

occurrences of the letter 'f'

No Comments

No Known Activations