INDEX

Explanations

code-related terms and parameters 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 @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

forRoot

-0.64

 виправивши

-0.59

шкан

-0.56

messageInfo

-0.54

GraphicsUnit

-0.53

ecore

-0.53

EReference

-0.53

fă

-0.53

 estekak

-0.52

脚注の使い方

-0.50

POSITIVE LOGITS

 vVar

0.66

 localObject

0.66

 paramInt

0.66

Демографія

0.64

 comod

0.64

 purpoſe

0.64

 iVar

0.62

 وتسجيلات

0.62

 ExecuteAsync

0.58

 bParam

0.57

Activations Density 0.034%

code-related terms and parameters in programming

No Comments

No Known Activations