INDEX

Explanations

technical terms and phrases related to data processing and statistical methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

mergeFrom

-0.56

 estekak

-0.55

ashimi

-0.54

amaño

-0.53

 regroupe

-0.52

ChildIndex

-0.52

 resourceCulture

-0.50

 initWithFrame

-0.49

entai

-0.49

posedge

-0.48

POSITIVE LOGITS

OGND

0.67

出版年

0.58

 dàng

0.56

 препратки

0.55

Personensuche

0.54

 rhestr

0.54

Datuak

0.53

 nahilalakip

0.52

 متعلقه

0.52

nodoc

0.51

Activations Density 1.644%

technical terms and phrases related to data processing and statistical methods

No Comments

No Known Activations