INDEX

Explanations

mathematical symbols and notation related to physical theories or models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

'{@

-0.79

 AssemblyTitle

-0.73

didSet

-0.68

SourceChecksum

-0.62

 通販

-0.62

DeleteBehavior

-0.58

NegativeButton

-0.58

enterOuterAlt

-0.57

numerusform

-0.57

ˈ

-0.57

POSITIVE LOGITS

 للمعارف

0.59

 noqa

0.55

nsic

0.55

rafat

0.53

 palp

0.53

 betweenstory

0.51

 technics

0.48

 linkovi

0.47

Hik

0.47

bone

0.47

Activations Density 0.495%

mathematical symbols and notation related to physical theories or models

No Comments

No Known Activations