INDEX

Explanations

numerical updates or entries, specifically related to data or results in a structured format

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

ranslated

-0.57

Петер

-0.56

 flé

-0.48

ništ

-0.48

']))

-0.48

']))

-0.47

 Crossword

-0.47

 vari

-0.46

Advertisement

-0.46

vá

-0.46

POSITIVE LOGITS

CloseOperation

0.77

 Wicidata

0.70

 CommonModule

0.69

May

0.66

 June

0.66

June

0.65

SpringBootTest

0.64

May

0.62

Tikang

0.59

Бележки

0.59

Activations Density 0.031%

numerical updates or entries, specifically related to data or results in a structured format

No Comments

No Known Activations