INDEX

Explanations

words related to privacy and account security, particularly in the context of online platforms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 प्रयास

-0.41

 trên

-0.40

-0.39

 contrats

-0.38

 inglês

-0.38

 déclarations

-0.37

 mixte

-0.37

 piuttosto

-0.37

ghter

-0.36

 efeitos

-0.36

POSITIVE LOGITS

 >=",

0.95

 Мексичка

0.86

 Majefty

0.84

Efq

0.82

 незавершена

0.82

aarrggbb

0.81

enumi

0.81

 Administrativna

0.80

enumii

0.80

 ostavi

0.78

Activations Density 0.077%

words related to privacy and account security, particularly in the context of online platforms

No Comments

No Known Activations