INDEX

Explanations

references to different versions or adaptations of products, services, or content

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

different versions or translations

np_acts-logits-general · gemini-2.0-flash

version

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 חיצוניים

-0.91

 betweenstory

-0.80

ViewImports

-0.79

 autorytatywna

-0.75

HasForeignKey

-0.72

ServletException

-0.71

はじめに

-0.70

RegistryLite

-0.70

Дереккөздер

-0.69

GraphicsUnit

-0.67

POSITIVE LOGITS

 version

3.72

 versions

3.05

version

2.98

 Version

2.75

 versión

2.72

 VERSION

2.66

Version

2.55

 versione

2.48

版本

2.47

 versão

2.43

Activations Density 0.761%

references to different versions or adaptations of products, services, or content

different versions or translations

version

No Comments

No Known Activations