INDEX

Explanations

medical terms and their associated data

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.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

 avoient

-0.53

 Técnica

-0.50

acta

-0.50

 Puoi

-0.49

 cliquez

-0.49

ometrics

-0.48

troppo

-0.48

crochet

-0.47

Efq

-0.47

ValueGenerated

-0.47

POSITIVE LOGITS

 autorytatywna

0.87



0.85

Билгалдахарш

0.75

 BoxFit

0.73

 nahilalakip

0.67

ContentAsync

0.61

olone

0.58

 مشين

0.57

MemoryWarning

0.56

مصادر

0.55

Activations Density 0.159%

medical terms and their associated data

No Comments

No Known Activations