INDEX

Explanations

scientific notations and mathematical expressions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</em>

-0.60

 виправивши

-0.56

Ordine

-0.54

 voud

-0.54

 Skill

-0.50

 amac

-0.50

ypeł

-0.49

 onderste

-0.48

们的

-0.48

们

-0.48

POSITIVE LOGITS

 '\\;'

1.12

 AttributeSet

1.08

webElementXpaths

0.97

principalColumn

0.96

IntoConstraints

0.95

énario

0.91

Personendaten

0.90

 كومونز

0.90

AsUp

0.89

ArgsConstructor

0.88

Activations Density 1.368%

scientific notations and mathematical expressions

No Comments

No Known Activations