INDEX

Explanations

adverbs indicating degree or intensity

oai_token-act-pair · gpt-3.5-turbo

adjectives indicating a high degree of quality or extremity

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

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

ortmund

-0.84

axter

-0.84

 Flavoring

-0.80

enaries

-0.79

rosis

-0.78

DragonMagazine

-0.78

adelphia

-0.77

culosis

-0.75

apses

-0.74

halla

-0.73

POSITIVE LOGITS

 versatile

1.36

 efficient

1.21

 useful

1.20

 easy

1.20

 expensive

1.19

 scalable

1.17

 accessible

1.16

 economical

1.16

 addictive

1.15

 effective

1.14

Activations Density 0.181%

adverbs indicating degree or intensity

adjectives indicating a high degree of quality or extremity

No Comments

No Known Activations