INDEX

Explanations

equality assignments 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 @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 disambiguazione

-0.74

InvalidProtocol

-0.53

MLE

-0.53

 transfieras

-0.53

 cố

-0.51

AntiForgeryToken

-0.50

 समीक्षाओं

-0.50

+#+

-0.50

ModelForm

-0.49

Diweddarwch

-0.49

POSITIVE LOGITS

 étoient

0.70

Przypisy

0.68

webElementXpaths

0.68

tvguidetime

0.65

Tembelea

0.62

enderror

0.62

ieR

0.61

 ainfi

0.60

 dischar

0.59

 Mares

0.59

Activations Density 0.027%

equality assignments in programming contexts

No Comments

No Known Activations