INDEX

Explanations

references to different types of cards and card games

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 MonoBehaviour

-0.89

-0.85

 صوتيه

-0.84

 betweenstory

-0.82

cerely

-0.82

})]

-0.78

parsedMessage

-0.77

lihood

-0.76

]`

-0.76

Efq

-0.76

POSITIVE LOGITS

 Cards

1.96

 cards

1.95

 card

1.74

 Card

1.73

 CARD

1.70

cards

1.69

Cards

1.66

Card

1.60

 CARDS

1.60

CARD

1.59

Activations Density 0.117%

references to different types of cards and card games

No Comments

No Known Activations