INDEX

Explanations

expressions of gratitude or thanks

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

place

-0.73

 Construct

-0.72

Osc

-0.66

FO

-0.66

 Loft

-0.65

wide

-0.62

destruct

-0.62

 Fires

-0.62

mouth

-0.61

 Ultron

-0.61

POSITIVE LOGITS

 thank

0.94

giving

0.89

 acknowled

0.84

gements

0.83

 thanking

0.83

ĸļ

0.81

ingle

0.79

bly

0.77

ESCO

0.77

gments

0.77

Activations Density 0.014%

expressions of gratitude or thanks

expressions of gratitude

No Comments

No Known Activations