INDEX

Explanations

references to products and their associated tags in a programming context

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

])));

-0.61

Ch

-0.48

ISING

-0.46

Ju

-0.44

 Crow

-0.44

ised

-0.44

 World

-0.43

kv

-0.43

Cha

-0.43

])),

-0.43

POSITIVE LOGITS

 XCTest

0.80

 BeautifulSoup

0.78

 itſelf

0.77

脚注の使い方

0.75

disambiguation

0.73



0.72

 ويكيميديا

0.72

homonymie

0.71

 Schengen

0.70

хьтан

0.70

Activations Density 0.399%

references to products and their associated tags in a programming context

No Comments

No Known Activations