INDEX

Explanations

numerical data and references to groups or conditions in a study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 समीक्षाओं

-0.62

RegistryLite

-0.59

 Paglinawan

-0.56

 ويكيميديا

-0.56

 behavior

-0.55

 CreateTagHelper

-0.53

 désolés

-0.52

 Chwiliwch

-0.52

InvalidProtocol

-0.52

ParallelGroup

-0.52

POSITIVE LOGITS

ReusableCell

0.68

 ویکی‌پدیای

0.56

initComponents

0.52

 سكانية

0.50

၁

0.49

didSet

0.46

ंदीखरीदारी

0.46

englanniksi

0.46

__*/

0.45

epam

0.45

Activations Density 0.344%

numerical data and references to groups or conditions in a study

No Comments

No Known Activations