INDEX

Explanations

labels and indicators related to scenes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ostante

-0.80

hematical

-0.75

hitung

-0.72

 provisoire

-0.70

RetentionPolicy

-0.70

üyük

-0.68

 extensible

-0.68

autonomie

-0.67

úgó

-0.67

 cortas

-0.67

POSITIVE LOGITS

 scene

1.99

 scenes

1.91

 SCENE

1.85

 Scene

1.82

SceneManagement

1.70

 Scenes

1.63

scene

1.61

Scene

1.55

SCENE

1.54

Scenes

1.48

Activations Density 0.048%

labels and indicators related to scenes

No Comments

No Known Activations