INDEX

Explanations

words indicating updates or changes in a software or application context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 externi

-0.81

 nahilalakip

-0.79

 Wikimedijinoj

-0.78

 Italijanski

-0.78

archiviato

-0.77

Šaltiniai

-0.76

省市镇

-0.73

httphttps

-0.73

@[+][

-0.73

商品説明

-0.72

POSITIVE LOGITS

!("{

0.55

leyebilirsiniz

0.49

”:

0.48

Rhestr

0.47

0.46

”

0.46

ردن

0.46

[]

0.44

():

0.44

Activations Density 0.049%

words indicating updates or changes in a software or application context

No Comments

No Known Activations