INDEX

Explanations

names of places and associated geographic information

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

 GenerationType

-0.48

ashvili

-0.47

MultipartFile

-0.47

 supposing

-0.47

örgy

-0.46

msgTypes

-0.45

}}$\\

-0.45

 iNdEx

-0.45

bibitem

-0.45

 saper

-0.44

POSITIVE LOGITS

TintMode

0.69

 المعيارى

0.69

styleUrls

0.69

 MonoBehaviour

0.65

الحياه

0.64

Personensuche

0.63

HandlerContext

0.60

脚注の使い方

0.58

 Normdatei

0.57

clable

0.56

Activations Density 0.214%

names of places and associated geographic information

No Comments

No Known Activations