INDEX

Explanations

words related to participation and contributions in studies or research contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Tikang

-1.05

 noDo

-1.05

iastes

-0.90

存于互联网档案馆

-0.90

 AssemblyCulture

-0.86

WebVitals

-0.82

 Мексичка

-0.81

RectangleBorder

-0.80

InputBorder

-0.80

CppCodeGen

-0.79

POSITIVE LOGITS

Nie

0.39

getCause

0.38

null

0.37

 null

0.37

الدراسه

0.37

 urč

0.34

zzati

0.34

 appeal

0.34

をご覧

0.34

//-->

0.33

Activations Density 1.713%

words related to participation and contributions in studies or research contexts

No Comments

No Known Activations