INDEX

Explanations

repeated equality checks in the context of programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

EndProject

-0.74

StructEnd

-0.70

XmlEnum

-0.69

SharedDtor

-0.68

xaml

-0.63

 '\\;'

-0.63

Personensuche

-0.62

featureID

-0.61

/**

-0.59

ymce

-0.58

POSITIVE LOGITS

Equals

0.93

equals

0.87

 subs

0.71

subseteq

0.63

 Equals

0.63

 equals

0.61

 subset

0.56

startsWith

0.54

 onCreateView

0.53

 solitario

0.51

Activations Density 0.162%

repeated equality checks in the context of programming

No Comments

No Known Activations