INDEX

Explanations

mentions of a specific term or acronym, 'SM'

oai_token-act-pair · gpt-3.5-turbo

references to "SM" followed by numeric designations, indicating a focus on specific media or series

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĥãĥĪ

-0.73

Ved

-0.72

icular

-0.71

 Authorization

-0.71

 Frie

-0.70

 Lyme

-0.70

ãĤ¡

-0.69

 Gamergate

-0.68

Ã§a

-0.67

bart

-0.65

POSITIVE LOGITS

ITH

1.08

ART

0.98

ugg

0.97

ASH

0.95

iley

0.92

ooth

0.86

ould

0.86

oke

0.85

achine

0.85

amba

0.85

Activations Density 0.013%

mentions of a specific term or acronym, 'SM'

references to "SM" followed by numeric designations, indicating a focus on specific media or series

No Comments

No Known Activations