INDEX

Explanations

phrases related to legal and political contexts

oai_token-act-pair · gpt-3.5-turbo

special characters or unique symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Dupl

-0.72

wagen

-0.70

 Farn

-0.68

 Kitt

-0.65

izabeth

-0.65

 sacrific

-0.65

 conduc

-0.65

 destro

-0.63

 Eisen

-0.63

itaire

-0.62

POSITIVE LOGITS

ª

1.13

Ĵ

1.09

¹

0.99

ł

0.97

Ĳ

0.96

ĳ

0.95

¼

0.92

ı

0.91

³

0.90

Ĥ

0.90

Activations Density 0.103%

phrases related to legal and political contexts

special characters or unique symbols

No Comments

No Known Activations