INDEX

Explanations

references to specific companies and products, particularly in the tech and automotive sectors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

verwijspagina

-0.68

ритори

-0.60

ToScroll

-0.60

 gainera

-0.60

Rüyada

-0.59

Autoritní

-0.57

oa̍t

-0.57

uxxxx

-0.57

HtmlAttribute

-0.55

IntoConstraints

-0.54

POSITIVE LOGITS

®

0.69

 صوتيه

0.63

®-

0.59

®

0.58

®,

0.57

 AssemblyCompany

0.56

 Corporation

0.55

 الحره

0.55

 corporation

0.54

éges

0.54

Activations Density 0.483%

references to specific companies and products, particularly in the tech and automotive sectors

No Comments

No Known Activations