INDEX

Explanations

references to the Star Wars universe, including its characters and themes

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

"user"

np_acts-logits-general · gemini-2.0-flash

Sithon

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 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

 voeten

-0.39

 arquitecto

-0.37

kelijke

-0.36

 venuto

-0.36

 amores

-0.35

 medarbe

-0.35

 atletas

-0.35

Melhor

-0.34

 servidores

-0.34

nė

-0.33

POSITIVE LOGITS

 Yoda

0.70

patine

0.69

 Skywalker

0.63

 Jedi

0.63

 lightsaber

0.63

 Kenobi

0.62

Yoda

0.60

 yoda

0.60

Jedi

0.59

 Mandalorian

0.57

Activations Density 0.201%

references to the Star Wars universe, including its characters and themes

"user"

Sithon

No Comments

No Known Activations