INDEX

Explanations

names of authors or contributors and their acknowledgments in research papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 فريبيس

-0.79

 AssemblyCulture

-0.65

SceneManagement

-0.60

 المرجع

-0.57

下载附件

-0.57

 piele

-0.56

Siddhartha

-0.56

MENAFN

-0.55

OwnProperty

-0.55

っこう

-0.54

POSITIVE LOGITS

 Urban

0.51

 Step

0.50

Jur

0.49

Pet

0.46

Pop

0.46

Urban

0.45

Top

0.45

URBAN

0.45

 Bond

0.44

Tom

0.44

Activations Density 0.222%

names of authors or contributors and their acknowledgments in research papers

No Comments

No Known Activations