INDEX

Explanations

mentions of costumes

oai_token-act-pair · gpt-3.5-turbo

references to costumes

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

venants

-0.83

-0.79

upon

-0.73

utherford

-0.72

orio

-0.71

 antidepressants

-0.68

raltar

-0.68

tical

-0.67

ntil

-0.66

fram

-0.65

POSITIVE LOGITS

 costumes

1.01

 costume

0.96

 worn

0.82

 Costume

0.81

 jewelry

0.80

 wearer

0.79

 attire

0.78

 apparel

0.77

pole

0.71

 wardrobe

0.67

Activations Density 0.018%

mentions of costumes

references to costumes

No Comments

No Known Activations