INDEX

Explanations

technical terms and references related to software programming and licensing conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

toMatch

-0.51

 résister

-0.51

 tendenza

-0.50

 conseguenza

-0.49

RenderAtEndOf

-0.49

ódó

-0.48

 Lived

-0.47

Jîn

-0.47

 publiques

-0.47

 tendencia

-0.46

POSITIVE LOGITS

 بيها

0.71

Rüyada

0.64

èdia

0.59

SuppressLint

0.56

 autorytatywna

0.55

存于互联网档案馆

0.55

EndGlobal

0.54

avadoc

0.53

 AssemblyProduct

0.52

stdafx

0.52

Activations Density 0.414%

technical terms and references related to software programming and licensing conditions

No Comments

No Known Activations