INDEX

Explanations

references to television and related devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

)$/,

-0.81

 Salta

-0.68

EndProject

-0.66

Vah

-0.66

%;">

-0.65

ARCHITECT

-0.64

 Perd

-0.62

 JpaRepository

-0.62

})}

-0.62

strokeWeight

-0.62

POSITIVE LOGITS

TV

2.34

 television

2.28

tv

2.05

 Television

1.96

TV

1.94

television

1.92

Tv

1.87

Television

1.85

 televisions

1.85

tv

1.78

Activations Density 0.068%

references to television and related devices

No Comments

No Known Activations