INDEX

Explanations

references to television

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AndEndTag

-0.80

adpleegd

-0.71

)$/,

-0.70

($(

-0.69

 Salta

-0.68

Ibid

-0.66

 AssemblyVersion

-0.66

AddTagHelper

-0.66

Читайте

-0.64

EndProject

-0.63

POSITIVE LOGITS

TV

3.29

tv

2.82

TV

2.78

 television

2.76

Tv

2.51

tv

2.49

 Television

2.41

TVs

2.34

television

2.30

Television

2.24

Activations Density 0.057%

references to television

No Comments

No Known Activations