INDEX

Explanations

phrases related to data privacy and confidentiality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

)$/,

-0.51

ROIT

-0.51

 Хорошо

-0.49

nsf

-0.46

THISDAY

-0.46

 nisi

-0.44

 leider

-0.44

ref

-0.44

 Apare

-0.44

BASEPATH

-0.43

POSITIVE LOGITS

SharedCtor

0.73

脚注の使い方

0.72

rungsseite

0.68

parsedMessage

0.65

徊

0.64

CloseOperation

0.63

 nahilalakip

0.63

 ویکی‌پدی

0.63

 دیکھیے

0.62

 مشين

0.62

Activations Density 0.605%

phrases related to data privacy and confidentiality

No Comments

No Known Activations