INDEX

Explanations

phrases or words related to common occurrences or practices

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

0000000000000000

-0.89

ById

-0.76

username

-0.71

FontSize

-0.70

iola

-0.70

aca

-0.70

inson

-0.69

stroke

-0.69

govtrack

-0.68

piece

-0.68

POSITIVE LOGITS

 academia

1.22

 Europe

1.04

 classrooms

0.96

 lieu

0.95

 conjunction

0.95

 contexts

0.95

 contemporary

0.93

 relation

0.93

 societies

0.92

 regards

0.92

Activations Density 0.251%

phrases or words related to common occurrences or practices

No Comments

No Known Activations