INDEX

Explanations

programming-related terms, particularly those associated with data manipulation and function execution

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

 TextAppearance

-0.83

 SwitchCompat

-0.77

 crdi

-0.76

VIAF

-0.74

 ſind

-0.73

 itſelf

-0.72

 autorytatywna

-0.72

 becauſe

-0.71

*/

-0.70

 photolibrary

-0.70

POSITIVE LOGITS

 EdgeInsets

0.78

BeginInit

0.74

UpInside

0.73

 AssemblyCompany

0.71

EndInit

0.70

 CGRectMake

0.67

GEBURTSDATUM

0.63

CGRectMake

0.62

PageRoute

0.61

Activations Density 0.327%

programming-related terms, particularly those associated with data manipulation and function execution

No Comments

No Known Activations