INDEX

Explanations

references to applications and their configurations

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

VIAF

-0.91

SourceChecksum

-0.87

❹

-0.83

Viited

-0.83

Personendaten

-0.81

ighed

-0.79

]")]

-0.79

SequentialGroup

-0.77

imetsu

-0.77

AndEndTag

-0.76

POSITIVE LOGITS

app

1.49

App

1.48

 apps

1.39

App

1.38

APP

1.36

getApp

1.29

APP

1.28

 Apps

1.26

app

1.21

Apps

1.21

Activations Density 0.095%

references to applications and their configurations

No Comments

No Known Activations