INDEX

Explanations

prepositions and phrases indicating relationships or connections between concepts

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

IsMutable

-0.61

ukone

-0.50

>");

-0.49

Personensuche

-0.48

 dàng

-0.47

>`;

-0.46

 newOwner

-0.44

 inne

-0.41

kungen

-0.41

Numerology

-0.41

POSITIVE LOGITS

 चीज़ों

0.83

createServer

0.74

medriver

0.74

 BoxDecoration

0.73

tvguidetime

0.72

 للمعارف

0.71

تقاوى

0.71

esModule

0.70

idalgo

0.69

auteuil

0.68

Activations Density 1.325%

prepositions and phrases indicating relationships or connections between concepts

No Comments

No Known Activations