INDEX

Explanations

numeric data related to research metrics and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AnchorStyles

-0.82

labelledby

-0.71

'],$

-0.69

SetFont

-0.68

Personensuche

-0.67

 تضيفلها

-0.64

igrette

-0.64

ården

-0.63

 sessionFactory

-0.62

#![

-0.61

POSITIVE LOGITS

 Malabar

0.66

Джерела

0.58

subsubsection

0.55

expandindo

0.55

 usaha

0.54

 indios

0.53

$__

0.52

 JUGA

0.52

ChildIndex

0.51

 Muscular

0.51

Activations Density 1.170%

numeric data related to research metrics and identifiers

No Comments

No Known Activations