INDEX

Explanations

phrases indicating relationships or connections between elements

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

ionView

-0.66

 createState

-0.64

posedge

-0.63

}`}>

-0.58

日閲覧

-0.56

InjectMocks

-0.55

Ọ

-0.53

Hentet

-0.53

 eventdata

-0.52

MENAFN

-0.52

POSITIVE LOGITS

AndroidJUnit

0.67

ๆ

0.67

-------------</

0.65

picasso

0.61

tanleria

0.59

ๆ

0.59

 мәкалә

0.56

titleMargin

0.56

طلحات

0.55

كويكب

0.55

Activations Density 1.055%

phrases indicating relationships or connections between elements

No Comments

No Known Activations