INDEX

Explanations

phrases related to making suitable choices or selections based on specific needs or criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 reden

-0.49

 Verify

-0.47

͘

-0.46

 vors

-0.45

Javadoc

-0.44

illust

-0.43

apnews

-0.43

kao

-0.43

illustration

-0.42

rimir

-0.41

POSITIVE LOGITS

 surla

0.82

kloped

0.72

mybatisplus

0.70

 FetchType

0.70

 ویکی‌پدی

0.67

Vidite

0.66

zzleHttp

0.66

 viewType

0.66

Искәрмәләр

0.65

DockStyle

0.65

Activations Density 0.320%

phrases related to making suitable choices or selections based on specific needs or criteria

No Comments

No Known Activations