INDEX

Explanations

syntax elements in code, specifically focusing on operations involving functions and method calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ویکی‌پدیا

-0.55

 насељу

-0.55

 مشين

-0.54

Activités

-0.50

thâu

-0.47

UseVisualStyle

-0.47

scriptcase

-0.47

aarrggbb

-0.46

AllowUser

-0.45

])):

-0.45

POSITIVE LOGITS

nestjs

0.54

izr

0.54

omenclature

0.52

GEBURTSDATUM

0.50

 Them

0.50

CSI

0.50

InputBorder

0.49

HideFlags

0.49

ArgsConstructor

0.49

writeFieldEnd

0.49

Activations Density 0.136%

syntax elements in code, specifically focusing on operations involving functions and method calls

No Comments

No Known Activations