INDEX

Explanations

references to "fat" and its variations in context

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

<bos>

-2.55

-0.83

ⓧ

-0.73

/**

-0.68

 rehabilitate

-0.66

Autoritní

-0.66

<?

-0.65

 autorytatywna

-0.60

 endow

-0.60

/*

-0.58

POSITIVE LOGITS

fat

1.32

Fat

1.32

Fat

1.29

fat

1.20

FAT

1.11

FAT

1.10

 fats

0.95

essica

0.90

 maroc

0.89

capulco

0.89

Activations Density 0.045%

references to "fat" and its variations in context

No Known Activations