INDEX

Explanations

concepts of proximity or closeness in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ดย

-0.83

QMetaType

-0.82

IsMutable

-0.80

upol

-0.79

Abp

-0.77

queryInterface

-0.77

PhysRev

-0.76

 chi̍t

-0.74

ModelAdmin

-0.74

 Wheeler

-0.73

POSITIVE LOGITS

 close

1.50

 Close

1.44

 CLOSE

1.42

 Closer

1.36

 closer

1.33

CLOSE

1.29

close

1.26

Close

1.24

 proximity

1.23

 Clos

1.21

Activations Density 0.076%

concepts of proximity or closeness in various contexts

No Comments

No Known Activations