INDEX

Explanations

content related to television viewing and its impact on audiences

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

Television or TV

np_acts-logits-general · gemini-2.0-flash

watching television or TV

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

jegy

-0.41

ObjectContext

-0.41

ATP

-0.39

biome

-0.38

ATP

-0.38

ungeon

-0.38

mile

-0.37

tudiant

-0.36

MOQ

-0.36

Signature

-0.36

POSITIVE LOGITS

 television

2.18

TV

2.11

tv

1.89

 Television

1.88

 televisions

1.80

TV

1.80

Television

1.75

television

1.74

 televis

1.71

TVs

1.69

Activations Density 0.192%

content related to television viewing and its impact on audiences

Television or TV

watching television or TV

No Comments

No Known Activations