INDEX

Explanations

technical specifications and definitions related to programming and software

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tifikasi

-0.56

Bioaccumulative

-0.54

 SDLK

-0.54

decorate

-0.54

stylesheet

-0.53

HMM

-0.52

thirsty

-0.52

 provisoire

-0.52

vaadin

-0.52

 ElementRef

-0.51

POSITIVE LOGITS

 autorytatywna

0.73

 Infórmanos

0.67

 beginnetje

0.67

 gawas

0.65

новниш

0.65

 мәкалә

0.64

 nahilalakip

0.64

 الرياضيه

0.62

 дописавши

0.61

پیوند

0.61

Activations Density 0.075%

technical specifications and definitions related to programming and software

No Comments

No Known Activations