INDEX

Explanations

references to roles and relationships among individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

StringBuffer

-0.52

λιο

-0.50

niczka

-0.50

 referenties

-0.49

laient

-0.48

 relativa

-0.48

恵

-0.47

scriptcase

-0.46

 insulting

-0.46

 aiding

-0.46

POSITIVE LOGITS

RegistryLite

0.70

ScopeManager

0.66

mybatisplus

0.61

uxxxx

0.61

djangoproject

0.59

 متعلقه

0.57

lgari

0.55

contentInset

0.54

 Winaray

0.54

addContainerGap

0.54

Activations Density 0.132%

references to roles and relationships among individuals

No Comments

No Known Activations