INDEX

Explanations

references to counterfeit money or banking systems

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

currency or coinage

np_acts-logits-general · gemini-2.0-flash

coins, currency, metals, medals

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

 Roskov

-0.72

migrationBuilder

-0.60

الحياه

-0.59

offsetof

-0.57

 MonoBehaviour

-0.57

Expedia

-0.56

:✨

-0.53

 prostagland

-0.53

WindowConstants

-0.52

 DialogInterface

-0.52

POSITIVE LOGITS

 coin

1.28

 coins

1.20

coin

1.13

 Coin

1.12

Coin

1.12

 minted

1.05

 coinage

1.03

coins

0.95

 mint

0.94

 Coins

0.94

Activations Density 0.098%

references to counterfeit money or banking systems

currency or coinage

coins, currency, metals, medals

No Comments

No Known Activations