INDEX

Explanations

references to activity levels

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

InteropServices

-0.68

Lähteet

-0.66

 cherchés

-0.65

GOTREF

-0.65

rrggbb

-0.65

\}\\

-0.64

Portail

-0.64

famous

-0.63

elebr

-0.63

mandu

-0.62

POSITIVE LOGITS

 activity

1.85

activity

1.49

 Activity

1.37

 ACTIVITY

1.35

 actividad

1.22

 Aktivität

1.17

activité

1.12

ACTIVITY

1.00

 activité

0.97

 atividade

0.95

Activations Density 0.150%

references to activity levels

No Comments

No Known Activations