INDEX

Explanations

character names and their corresponding roles in movies or shows

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 editados

-0.53

 écou

-0.48

]))

-0.45

 newBuilder

-0.44

ebilir

-0.43

 commerciali

-0.43

 trabalhadores

-0.43

".

-0.42

}');

-0.42

مح

-0.42

POSITIVE LOGITS

DeleteBehavior

0.79

 незавершена

0.78

InjectAttribute

0.78

 portraying

0.77

 portrayal

0.76

AccessorTable

0.75

 portray

0.74

SceneManagement

0.74

 portrays

0.72

mybatisplus

0.71

Activations Density 0.085%

character names and their corresponding roles in movies or shows

No Comments

No Known Activations