INDEX

Explanations

references to brands in the text

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

LogFactory

-0.85

 Cytometry

-0.80

Дереккөздер

-0.78

 Wentworth

-0.78

готовка

-0.77

 Sculpture

-0.75

hmigung

-0.73

CWE

-0.73

 Ziegler

-0.73

ցված

-0.72

POSITIVE LOGITS

 BRAND

1.26

brands

1.24

BRAND

1.23

brand

1.23

Brands

1.20

 brand

1.20

 brands

1.19

 Brand

1.15

Brand

1.12

 Brands

1.09

Activations Density 0.006%

references to brands in the text

No Comments

No Known Activations