INDEX

Explanations

terms related to the concept of inclusion and factors contributing to various classifications or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 honte

-0.60

 croire

-0.59

 whoſe

-0.57

 LoggerFactory

-0.56

 ordinaria

-0.56

 judiciaire

-0.55

*++

-0.54

frente

-0.54

 Cæsar

-0.54

 tarko

-0.53

POSITIVE LOGITS

 ModelExpression

0.96

 inclusion

0.92

 include

0.91

 Include

0.86

 includes

0.83

 incorporate

0.83

 incorporating

0.81

 Inclusion

0.80

 INCLUDE

0.79

 incorporation

0.79

Activations Density 0.774%

terms related to the concept of inclusion and factors contributing to various classifications or assessments

No Comments

No Known Activations