INDEX

Explanations

the word "makeup"

oai_token-act-pair · gpt-4-turbo

references to makeup and cosmetics

oai_token-act-pair · gpt-3.5-turbo

references to makeup and cosmetics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Fal

-0.77

âķĲâķĲ

-0.71

 Chronicle

-0.68

ron

-0.68

self

-0.68

ARR

-0.67

 Hammond

-0.66

Bull

-0.66

Hill

-0.63

 Published

-0.63

POSITIVE LOGITS

 makeup

1.29

 cosmetics

0.82

ometry

0.80

 wardrobe

0.80

ratulations

0.77

creen

0.77

metics

0.76

ĸļ

0.76

wig

0.75

 dermat

0.74

Activations Density 0.008%

the word "makeup"

references to makeup and cosmetics

references to makeup and cosmetics

No Comments

No Known Activations