INDEX

Explanations

terms related to enabling or disabling features and functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

articolo

-0.44

incontro

-0.43

 Meksi

-0.42

ījum

-0.39

 zaken

-0.38

 artesanato

-0.38

ycz

-0.38

mengen

-0.37

Veuillez

-0.37

 reseña

-0.37

POSITIVE LOGITS

 Савезне

0.89

 OnEnable

0.87

IntoConstraints

0.85

 uſed

0.83

 Activate

0.80

 queſta

0.79

 activate

0.79

FunctionFlags

0.76

istoitu

0.75

 faſt

0.74

Activations Density 0.298%

terms related to enabling or disabling features and functionalities

No Comments

No Known Activations