INDEX

Explanations

mentions of the word "Walmart" and its variations

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 minggu

-0.70

 själ

-0.66

ροσ

-0.66

Сла

-0.66

lichkeit

-0.65

ness

-0.63

Obr

-0.63

#__

-0.62

 lluvias

-0.61

alini

-0.61

POSITIVE LOGITS

 Walters

1.62

Wal

1.57

WAL

1.52

wal

1.40

Wal

1.39

 Walden

1.31

 Walton

1.28

WAL

1.23

 Walpole

1.10

 walnuts

1.09

Activations Density 0.005%

mentions of the word "Walmart" and its variations

No Comments

No Known Activations