INDEX

Explanations

terms related to card games and gameplay mechanics

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

Playing card context

np_acts-logits-general · gemini-2.0-flash

card suit

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ValueStyle

-0.66

 ddelweddau

-0.64

 phosphorylation

-0.63

 phosphory

-0.60

MessageTagHelper

-0.59

 Calvo

-0.59

RenderAtEndOf

-0.58

 vivement

-0.58

SourceChecksum

-0.54

parsedMessage

-0.54

POSITIVE LOGITS

 deck

1.20

 cards

1.18

 card

1.07

 decks

1.00

 Deck

0.96

cards

0.95

deck

0.94

Deck

0.90

 suit

0.89

 Cards

0.89

Activations Density 0.150%

terms related to card games and gameplay mechanics

Playing card context

card suit

No Comments

No Known Activations