INDEX

Explanations

functional references and structures in programming or 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 @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Shet

-0.81

QMetaType

-0.73

 Kett

-0.72

 Atwood

-0.70

ogeneous

-0.69

labus

-0.69

 Schuld

-0.68

ütü

-0.68

vett

-0.68

setOnItem

-0.68

POSITIVE LOGITS

)(

0.81

Хьажоргаш

0.79

)^{

0.78

 Monfieur

0.76

*)(

0.76

 Garrick

0.75

 Teixeira

0.72

expandindo

0.70

 Theſe

0.70

 doubtnut

0.69

Activations Density 0.265%

functional references and structures in programming or mathematical expressions

No Comments

No Known Activations