INDEX

Explanations

mathematical formatting and equations

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

IFrame

Link

Negative Logits

udas

-0.56

alai

-0.54

 Weing

-0.54

სქოლიო

-0.54

 Edmunds

-0.53

libft

-0.53

(""),

-0.52

llllllll

-0.52

thog

-0.51

ZING

-0.51

POSITIVE LOGITS

ScopeManager

0.77

IonicModule

0.74

ValueGeneration

0.74

ConverterFactory

0.74

脚注の使い方

0.70

yntaxException

0.67

CodeAttribute

0.65

DrawerToggle

0.64

المناصب

0.63

icoot

0.63

Activations Density 0.044%

mathematical formatting and equations

No Known Activations