INDEX

Explanations

keywords related to image captions or descriptions

oai_token-act-pair · gpt-3.5-turbo

references to photographs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

merce

-0.89

nder

-0.80

ority

-0.74

ught

-0.73

stood

-0.68

bid

-0.67

 gentleman

-0.66

atri

-0.66

 congress

-0.66

tainment

-0.66

POSITIVE LOGITS

 Photos

1.22

Photos

1.16

ynthesis

1.02

Gallery

0.98

OTOS

0.94

 Thumbnails

0.92

 Picks

0.89

 Annotations

0.88

 Caption

0.87

 Photographer

0.86

Activations Density 0.004%

keywords related to image captions or descriptions

references to photographs

No Comments

No Known Activations