INDEX

Explanations

photographs or images

oai_token-act-pair · gpt-3.5-turbo

references to files and photos

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iatric

-0.76

astically

-0.75

ressive

-0.75

asons

-0.74

chanted

-0.72

ace

-0.71

cffff

-0.70

depth

-0.70

bard

-0.69

bol

-0.69

POSITIVE LOGITS

 IMAGES

0.82

 caption

0.79

 Photographer

0.74

HAEL

0.73

 Uriel

0.72

 Courtesy

0.70

 photo

0.70

 courtesy

0.69

 Aerial

0.68

 depicting

0.67

Activations Density 0.060%

photographs or images

references to files and photos

No Comments

No Known Activations