INDEX

Explanations

phrases related to evaluation and analysis in research contexts

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

 ويكيپيديا

-0.68

 VIAF

-0.68

 JAXBElement

-0.66

centiles

-0.59

sidemargin

-0.57

zepine

-0.56

Injured

-0.56

Spoljašnje

-0.55

 EClass

-0.54

typeorm

-0.54

POSITIVE LOGITS

 across

2.77

across

2.50

 Across

2.44

Across

2.35

 ACROSS

2.20

 spanning

1.35

 lintas

1.22

 cross

1.21

spanning

1.16

跨

1.15

Activations Density 0.558%

phrases related to evaluation and analysis in research contexts

No Comments

No Known Activations