INDEX

Explanations

mathematical terms and symbols related to set theory and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

MigrationBuilder

-0.76

 Jefus

-0.62

 OnTrigger

-0.61

 itſelf

-0.59

 theſe

-0.57

IntoConstraints

-0.57

usermodel

-0.56

 greateſt

-0.56

 Clarence

-0.56

 INTERESAR

-0.54

POSITIVE LOGITS

 whose

0.63

 ModelExpression

0.61

 that

0.59

 utafitiHapana

0.58

SourceChecksum

0.55

 which

0.53

Jeografia

0.49

 cuja

0.49

XmlAccessorType

0.49

lograph

0.48

Activations Density 0.780%

mathematical terms and symbols related to set theory and functions

No Comments

No Known Activations