INDEX

Explanations

content related to movies or cinematic elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

logic

-0.43

 Black

-0.43

term

-0.42

me

-0.42

-0.41

lo

-0.41

ghi

-0.41

Black

-0.40

life

-0.40

anne

-0.40

POSITIVE LOGITS

 للمعارف

0.95

AsUp

0.82

 تانيه

0.81

 متعلقه

0.78

jspx

0.78

 ddelweddau

0.75

letoe

0.73

 Baillargeon

0.71

 doubtnut

0.71

ArrowToggle

0.70

Activations Density 0.279%

content related to movies or cinematic elements

No Comments

No Known Activations