INDEX

Explanations

references to giant entities or beings

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

Kura

-0.67

Karin

-0.65

-0.64

mathscr

-0.63

aliana

-0.63

 bParam

-0.63

 colspan

-0.62

Set

-0.61

UrlResolution

-0.61

malar

-0.60

POSITIVE LOGITS

 Giants

1.42

 Giant

1.29

giant

1.25

Giant

1.19

Giants

1.17

 giants

1.10

 giant

1.00

 géant

0.98

 gigante

0.91

IBOutlet

0.87

Activations Density 0.006%

references to giant entities or beings

No Comments

No Known Activations