INDEX

Explanations

technical terms and programming syntax

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

gr

-0.46

<",

-0.46

Gr

-0.45

 autorytatywna

-0.45

dr

-0.45

Gr

-0.44

tele

-0.43

inga

-0.42

 COLOUR

-0.41

nao

-0.41

POSITIVE LOGITS

UnsafeEnabled

0.93

mybatisplus

0.90

apunov

0.83

 SafeMath

0.81

 transfieras

0.79

WebVitals

0.72

 disponibilités

0.69

 ModelExpression

0.69

 Réponses

0.68

 JpaRepository

0.66

Activations Density 0.171%

technical terms and programming syntax

No Comments

No Known Activations