INDEX

Explanations

phrases and terms relating to targeted communication and advertising strategies

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

 MonoBehaviour

-0.57

ēc

-0.51

ginous

-0.49

moine

-0.48

 movement

-0.47

 Juda

-0.47

thâu

-0.47

sinon

-0.46

ContextCompat

-0.46

 sida

-0.46

POSITIVE LOGITS

Audience

0.88

 Targeting

0.86

targeted

0.85

 targeted

0.84

 audience

0.83

 Audience

0.83

audience

0.80

 target

0.80

 targeting

0.79

 audiences

0.79

Activations Density 0.173%

phrases and terms relating to targeted communication and advertising strategies

No Comments

No Known Activations