INDEX

Explanations

intensifiers that emphasize the degree of an adjective or adverb

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disambiguazione

-0.52

 externi

-0.42

embols

-0.41

任何人

-0.41

vų

-0.40

homonymie

-0.39

ISPR

-0.39

bės

-0.37

Parms

-0.36

POSITIVE LOGITS

 less

0.70

 fewer

0.68

 Fewer

0.65

 weniger

0.61

 Less

0.61

 milder

0.56

 lesser

0.55

 softer

0.52

 LESS

0.52

]=>

0.52

Activations Density 0.133%

intensifiers that emphasize the degree of an adjective or adverb

No Comments

No Known Activations