INDEX

Explanations

technical terms and references related to coding and component context 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

setVerticalGroup

-0.66

eced

-0.53

 Both

-0.52

 common

-0.50

Bir

-0.50

ælp

-0.49

 both

-0.48

otriz

-0.48

mma

-0.48

POSITIVE LOGITS

 useRouter

0.92

tagext

0.88

ſelf

0.74

 useParams

0.73

 المعيارى

0.72

 houſe

0.70

 Majefty

0.70

 IndexPath

0.67

 createState

0.67

ſelves

0.66

Activations Density 0.566%

technical terms and references related to coding and component context in programming

No Comments

No Known Activations