INDEX

Explanations

numerical values and references to legal processes and standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Хьажоргаш

-0.89

PreferredItem

-0.89

bootstrapcdn

-0.88

 saites

-0.78

 pinulongan

-0.77

 ElementRef

-0.73

(&:

-0.73

}{@

-0.71

 AssemblyCulture

-0.71

WebElementEntity

-0.71

POSITIVE LOGITS

 lähe

0.43

 näin

0.43

UnusedPrivate

0.42

MIDDLEWARE

0.41

Thus

0.41

 pihaknya

0.41

While

0.40

ugy

0.40

leyici

0.39

dė

0.39

Activations Density 0.314%

numerical values and references to legal processes and standards

No Comments

No Known Activations