INDEX

Explanations

references to wearing or not wearing specific items of clothing

oai_token-act-pair · gpt-3.5-turbo

instances of the word "wear" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aminer

-0.75

=-=-=-=-

-0.74

 Debor

-0.71

demon

-0.71

estine

-0.70

raction

-0.69

akespeare

-0.68

heid

-0.67

yrinth

-0.65

ommod

-0.65

POSITIVE LOGITS

 apparel

1.13

 clothing

1.02

 jeans

1.01

 worn

1.00

 gloves

0.97

 underwear

0.96

 diapers

0.96

 clothes

0.95

 shoes

0.93

 shirts

0.91

Activations Density 0.041%

references to wearing or not wearing specific items of clothing

instances of the word "wear" and its variations

No Comments

No Known Activations