INDEX

Explanations

technical terms related to options and configurations in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 للاسماء

-0.87

expandindo

-0.85

IndentedString

-0.75

󠁢

-0.73

ollectionView

-0.73

 مشين

-0.72

 >=",

-0.72

 Normdatei

-0.70

tvguidetime

-0.69

клопе

-0.69

POSITIVE LOGITS

CreateInfo

0.59

 ujednoznacz

0.53

 informations

0.48

 json

0.47

 StatelessWidget

0.47

Props

0.46

摘要

0.45

json

0.44

Flags

0.44

 segü

0.44

Activations Density 0.496%

technical terms related to options and configurations in programming contexts

No Comments

No Known Activations