INDEX

Explanations

programming-related terminology and concepts, particularly methods and properties related to code structure and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

sizeCache

-0.81

AccessorTable

-0.73

DrawerToggle

-0.72

GraphicsUnit

-0.62

 disambiguazione

-0.62

XmlAccessType

-0.60

WriteBarrier

-0.57

ArgsConstructor

-0.57

getColumnIndex

-0.56

ContextHolder

-0.54

POSITIVE LOGITS

 compound

0.63

 group

0.53

 regular

0.52

 procedure

0.50

 reserved

0.49

Raw

0.49

 Group

0.48

 composite

0.48

 special

0.47

 named

0.47

Activations Density 0.881%

programming-related terminology and concepts, particularly methods and properties related to code structure and syntax

No Comments

No Known Activations