INDEX

Explanations

patterns related to scheduling and program titles in media broadcasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

الحياه

-0.69

UnusedPrivate

-0.67

GEBURTSDATUM

-0.62

buttonBar

-0.59

 station

-0.57

ManagedBean

-0.57

 grade

-0.57

 commission

-0.57

anum

-0.56

 NavController

-0.55

POSITIVE LOGITS

 others

1.50

others

1.25

etc

1.23

 among

1.14

among

1.09

etc

1.08

 zelfs

1.06

 amongst

1.06

 lainnya

1.02

 persino

1.02

Activations Density 0.619%

patterns related to scheduling and program titles in media broadcasts

No Comments

No Known Activations