INDEX

Explanations

intensifiers or modifiers conveying emphasis or degree

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

ledem

-0.54

nik

-0.52

RenderAtEndOf

-0.50

渉

-0.49

 Tyre

-0.49

سطس

-0.48

âtel

-0.46

ंदीखरीदारी

-0.46

ագրություններ

-0.45

อาด

-0.45

POSITIVE LOGITS

uxxxx

0.73

 viewDidLoad

0.68

 Administrativna

0.67

CellStyle

0.65

 JpaRepository

0.64

 Chiefs

0.63

sitis

0.60

 >=",

0.59

GeneratedValue

0.59

 AssemblyTitle

0.59

Activations Density 0.385%

intensifiers or modifiers conveying emphasis or degree

No Comments

No Known Activations