INDEX

Explanations

words and phrases associated with app usage, shared resources, and user interactions with virtual machines

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

 spel

-0.48

Leg

-0.47

borderFill

-0.47

 pép

-0.46

моро

-0.46

burn

-0.45

ścią

-0.45

agrid

-0.45

ści

-0.44

neck

-0.44

POSITIVE LOGITS

expandindo

0.88

 fellow

0.78

adaptiveStyles

0.75

 Jefus

0.74

 sesama

0.74

 purpoſe

0.73

Portail

0.73

 Normdatei

0.73

Източници

0.72

tvguidetime

0.71

Activations Density 0.338%

words and phrases associated with app usage, shared resources, and user interactions with virtual machines

No Comments

No Known Activations