INDEX

Explanations

expressions of gratitude for viewing content such as "Thanks for watching."

oai_token-act-pair · gpt-3.5-turbo

phrases related to viewer engagement and interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

soDeliveryDate

-0.85

rencies

-0.74

inational

-0.74

wcs

-0.73

edIn

-0.73

paio

-0.69

akeru

-0.67

angular

-0.66

quartered

-0.65

uyomi

-0.64

POSITIVE LOGITS

 reader

0.70

 Spoiler

0.69

 Leah

0.65

 Sierra

0.64

 Sneak

0.63

Cly

0.63

!/

0.61

uo

0.61

 Sawyer

0.61

 Bust

0.60

Activations Density 0.070%

expressions of gratitude for viewing content such as "Thanks for watching."

phrases related to viewer engagement and interaction

No Comments

No Known Activations