INDEX

Explanations

references to specific scientific aims or objectives

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

 дописавши

-0.85

ณา

-0.84

 rolo

-0.79

licenses

-0.77

INA

-0.77

Loa

-0.76



-0.75

 Bryn

-0.73

 Chol

-0.73

 Coliseum

-0.72

POSITIVE LOGITS

1.65

sah

0.83

价比

0.81

ی

0.78

sted

0.73

0.71

Sud

0.70

sud

0.70

ים

0.67

Sheffield

0.65

Activations Density 0.003%

references to specific scientific aims or objectives

No Comments

No Known Activations