INDEX

Explanations

phrases indicating examples or instances

oai_token-act-pair · gpt-3.5-turbo

examples and references to various topics or subjects

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

querade

-0.78

hunt

-0.77

ettes

-0.76

culosis

-0.72

izons

-0.72

anamo

-0.72

Enlarge

-0.71

forts

-0.71

emies

-0.70

aughters

-0.70

POSITIVE LOGITS

how

1.31

why

1.22

 what

0.96

 hypocrisy

0.95

 unintended

0.93

 lazy

0.91

bip

0.85

 blatant

0.83

 collusion

0.82

 wasteful

0.82

Activations Density 0.106%

phrases indicating examples or instances

examples and references to various topics or subjects

No Comments

No Known Activations