INDEX

Explanations

references to mathematical or logical operations and transformations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Both

-0.53

 femininos

-0.53

 differenza

-0.50

 rozdí

-0.50

setof

-0.49

 plupart

-0.49

 aikana

-0.46

 mêmes

-0.46

 Both

-0.46

 banget

-0.45

POSITIVE LOGITS

ConstraintMaker

0.93

IsContent

0.93

 AssemblyCulture

0.90

 become

0.89

 manageable

0.88

NameInMap

0.88

menjadi

0.88

 something

0.87

become

0.87

CppMethod

0.85

Activations Density 0.498%

references to mathematical or logical operations and transformations

No Comments

No Known Activations