INDEX

Explanations

terms related to visual effects and image clarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 SqlCommand

-0.65

Nationalité

-0.58

 contextLoads

-0.57

 Arki

-0.56

IsMutable

-0.53

出版年

-0.53

kmäler

-0.52

teady

-0.52

openzeppelin

-0.52

ActionCreators

-0.51

POSITIVE LOGITS

fortawesome

0.57

nats

0.52

bumptech

0.52

 attirer

0.48

 texture

0.48

 RoutedEventArgs

0.47

 remplir

0.47

 unknownFields

0.47

зулта

0.47

 shadowy

0.47

Activations Density 0.356%

terms related to visual effects and image clarity

No Comments

No Known Activations