INDEX

Explanations

terms and references related to software licensing and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 يتيمه

-0.66

besondere

-0.63

 parameterized

-0.62

 leid

-0.57

httphttps

-0.56

 nyelven

-0.56

atrième

-0.56

Initializable

-0.55

getTop

-0.54

 daleko

-0.53

POSITIVE LOGITS

gms

3.14

gms

0.94

SerializeField

0.91

rxjs

0.75

mybatisplus

0.67

bitField

0.66

VIAF

0.66

gm

0.65

ecore

0.65

 الرياضيه

0.63

Activations Density 0.037%

terms and references related to software licensing and frameworks

No Comments

No Known Activations