INDEX

Explanations

words related to persuasion and convincing

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

 mulighed

-0.58

 याद

-0.57

fhir

-0.56

to

-0.54

nameLabel

-0.53

tación

-0.52

expo

-0.52

 beho

-0.52

 InputDecoration

-0.52

尽

-0.52

POSITIVE LOGITS

 persuaded

1.35

 persu

1.32

 persuasion

1.30

 convincing

1.23

 persuading

1.22

 convinces

1.22

 convinced

1.20

 persuasive

1.16

 convince

1.16

 persuade

1.15

Activations Density 0.008%

words related to persuasion and convincing

No Comments

No Known Activations