INDEX

Explanations

terms related to categorization and classification systems

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

mybatisplus

-0.82

 utafitiHapana

-0.78

addGap

-0.77

 متعلقه

-0.74

expandindo

-0.73

MigrationBuilder

-0.69

AsUp

-0.69

اریخ

-0.67

 незавершена

-0.67

bootstrapcdn

-0.67

POSITIVE LOGITS

Etymology

0.68

Etimo

0.60

 NAME

0.58

Etimología

0.55

 Names

0.54

 Name

0.54

Names

0.53

 Namens

0.52

 name

0.50

 gritos

0.50

Activations Density 0.001%

terms related to categorization and classification systems

No Comments

No Known Activations