INDEX

Explanations

database table definitions and their attributes

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

enumii

-0.71

 الرياضيه

-0.67

 propOrder

-0.67

Jereo

-0.64

 ویکی‌پدیا

-0.63

PhysRev

-0.62

Tembelea

-0.60

enumi

-0.60

 المعيارى

-0.60

featureID

-0.60

POSITIVE LOGITS

 متعلقه

0.66

 blob

0.57

big

0.56

blob

0.55

 NULL

0.52

 binary

0.51

 blobs

0.50

BLO

0.50

CLO

0.48

NV

0.48

Activations Density 0.349%

database table definitions and their attributes

No Comments

No Known Activations