INDEX

Explanations

mentions of people or entities wearing specific items or accessories

oai_token-act-pair · gpt-3.5-turbo

instances of the word "wearing."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

cffffcc

-0.81

=-=-=-=-

-0.73

 COUR

-0.69

later

-0.68

MQ

-0.66

demon

-0.66

deal

-0.65

izoph

-0.65

estine

-0.65

edia

-0.65

POSITIVE LOGITS

 apparel

0.94

 jeans

0.89

 worn

0.87

 clothing

0.84

 shoes

0.83

 clothes

0.80

ables

0.79

 robes

0.79

 underwear

0.79

ves

0.78

Activations Density 0.017%

mentions of people or entities wearing specific items or accessories

instances of the word "wearing."

No Comments

No Known Activations