INDEX

Explanations

acronyms and their associated meanings or contexts in professional documentation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 uska

-0.59

newtheorem

-0.47

tribune

-0.46

iseta

-0.46

 weren

-0.44

zahl

-0.44

jScrollPane

-0.44

jsdelivr

-0.43

 tout

-0.43

UrlResolution

-0.42

POSITIVE LOGITS

AsUp

0.90

SharedDtor

0.79

 Italijani

0.75

 bénévoles

0.71

 AppModule

0.71

ArgsConstructor

0.69

URLException

0.68

Zacks

0.66

★★★★☆

0.63

CWE

0.62

Activations Density 0.687%

acronyms and their associated meanings or contexts in professional documentation

No Comments

No Known Activations