INDEX

Explanations

sweet flavors or items

oai_token-act-pair · gpt-3.5-turbo

the word "sweet" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Downloadha

-1.28

ctica

-0.82

agnar

-0.74

 Shutterstock

-0.73

kson

-0.72

senal

-0.72

pora

-0.71

 Administ

-0.71

agall

-0.71

 Occupations

-0.69

POSITIVE LOGITS

heart

1.31

eners

1.30

ened

1.17

ener

1.12

bread

1.08

 potato

1.06

est

1.06

sweet

1.04

 sweet

1.02

ening

1.02

Activations Density 0.013%

sweet flavors or items

the word "sweet" and its variations in different contexts

No Comments

No Known Activations