INDEX

Explanations

specific scientific terminology and proper nouns, particularly in biological and medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 EconPapers

-0.86

 nahilalakip

-0.81

LookAnd

-0.67

ValueStyle

-0.66

 kasarigan

-0.58

reactstrap

-0.56

 Normdatei

-0.56

 հղումներ

-0.56

 externi

-0.55

setViewportView

-0.54

POSITIVE LOGITS

 ویکی‌پدیای

0.60

 contextLoads

0.55

GEBURTS

0.54

 purpoſe

0.49

 Modelo

0.48

 cauſe

0.48

 AppBundle

0.47

ように

0.46

aspectj

0.45

CLUS

0.44

Activations Density 1.458%

specific scientific terminology and proper nouns, particularly in biological and medical contexts

No Comments

No Known Activations