INDEX

Explanations

strings used in programming contexts, particularly related to user interface elements and settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Hozzáférés

-0.46

тере

-0.45

Бележки

-0.44

Források

-0.43

moveToFirst

-0.42

المناصب

-0.42

ิลป

-0.42

 vicenda

-0.42

 /\.(

-0.41

ArgumentParser

-0.41

POSITIVE LOGITS

0.75

 lenker

0.75

 bezeichneter

0.73

ंदीखरीदारी

0.72

 للمعارف

0.69

ollectionView

0.64

 fundido

0.60

 linkovi

0.60

 oxides

0.59

'):

0.59

Activations Density 0.100%

strings used in programming contexts, particularly related to user interface elements and settings

No Comments

No Known Activations