INDEX

Explanations

references to different scenes within a narrative

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

scene descriptions or scene management

np_acts-logits-general · gemini-2.0-flash

scene graph, recognition, management, editor

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 VIAF

-0.68

multer

-0.68

Datuak

-0.64

antMatchers

-0.63

ostante

-0.60

 سكانية

-0.59

damente

-0.58

 getBase

-0.57

 extensible

-0.57

gania

-0.56

POSITIVE LOGITS

 scenes

1.68

 scene

1.65

 SCENE

1.62

 Scene

1.55

 Scenes

1.45

scene

1.42

SCENE

1.41

Scenes

1.35

SceneManagement

1.32

Scene

1.29

Activations Density 0.077%

references to different scenes within a narrative

scene descriptions or scene management

scene graph, recognition, management, editor

No Comments

No Known Activations

references to different scenes within a narrative

scene descriptions or scene management

scene graph, recognition, management, editor

No Comments

No Known Activations