INDEX

Explanations

mathematical notation and references indicated by special characters, such as equations and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 فريبيس

-0.80

 незавершена

-0.72

ⓧ

-0.67

 utafitiHapana

-0.65

دانشنامهٔ

-0.63

:✨

-0.63

цездатний

-0.62

 للمعارف

-0.62

IVEREF

-0.62

 المعيارى

-0.62

POSITIVE LOGITS

0.75

 XNUMX

0.65

extAlignment

0.64

helves

0.63

"।

0.62

ябре

0.62

lossians

0.59

ulario

0.58

わずか

0.58

 møte

0.57

Activations Density 2.436%

mathematical notation and references indicated by special characters, such as equations and symbols

No Comments

No Known Activations