INDEX

Explanations

mathematical symbols and notations related to data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

<eos>

-0.69

.*")]

-0.51

↵↵

-0.51

日閲覧

-0.50

BeginInit

-0.49

 ویکی‌پدیای

-0.48

iches

-0.47

</tr>

-0.46

setVerticalGroup

-0.45

Ծանոթ

-0.45

POSITIVE LOGITS

ècie

0.74

ItemBackground

0.71

antMatchers

0.70

ⓧ

0.69

GEBURTS

0.69

évaluateur

0.67

XmlAccessorType

0.66

 nakalista

0.64

Контак

0.63

 logistique

0.63

Activations Density 0.223%

mathematical symbols and notations related to data analysis

No Comments

No Known Activations