INDEX

Explanations

details related to laboratory protocols and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 estimés

-0.90

 calendriers

-0.75

MethodManager

-0.75

 insuffisamment

-0.75

 يتيمه

-0.73

 nahilalakip

-0.72

 تضيفلها

-0.70

 الاطلاع

-0.69

Revenir

-0.68

POSITIVE LOGITS

 cappuccio

0.55

0.53

each

0.52

 cappello

0.51

PerformLayout

0.50

ưu

0.50

 each

0.49

 joyas

0.47

 préparé

0.46

 Reserve

0.45

Activations Density 0.333%

details related to laboratory protocols and measurements

No Comments

No Known Activations