INDEX

Explanations

phrases related to numerical or statistical data, especially those concerning research results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

:✨

-0.59

 мәкал

-0.53

+#+#

-0.53

 للاسماء

-0.47

 ErrIntOverflow

-0.46

scriptcase

-0.46

 getItemCount

-0.40

AsUp

-0.40

حوالہ

-0.38

sizeCache

-0.38

POSITIVE LOGITS

 Leopoldo

0.49

 Italijani

0.48

ẵn

0.47

 Brewer

0.47

WebpackPlugin

0.46

 Barbier

0.46

írus

0.45

pity

0.45

 Egger

0.45

stus

0.44

Activations Density 0.859%

phrases related to numerical or statistical data, especially those concerning research results

No Comments

No Known Activations