INDEX

Explanations

references to performance metrics and optimizations in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IANGLES

-0.57

writeFieldEnd

-0.56

mybatisplus

-0.56

ArgsConstructor

-0.55

parsedMessage

-0.54

InjectAttribute

-0.52

RegistryLite

-0.51

webhook

-0.51

 autorytatywna

-0.50

 مشارکت‌کنندگان

-0.50

POSITIVE LOGITS

 performance

0.73

 slowdown

0.72

slow

0.68

 slow

0.68

 slowing

0.68

performance

0.65

 speed

0.65

 optimization

0.63

 improvement

0.62

 Slow

0.59

Activations Density 0.180%

references to performance metrics and optimizations in programming

No Comments

No Known Activations