INDEX

Explanations

references to awards and recognition in news articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.86

XmlAccessType

-0.79

олові

-0.71

 makeStyles

-0.66

WithMany

-0.66

ientôt

-0.64

 Himo

-0.62

erover

-0.61

الإنجليزية

-0.61

EndGlobalSection

-0.59

POSITIVE LOGITS

expandindo

0.64

Tembelea

0.59

KommentareTeilen

0.57

news

0.54

IntoConstraints

0.54

 EconPapers

0.52

ieteur

0.52

News

0.51

 News

0.51

 news

0.49

Activations Density 0.111%

references to awards and recognition in news articles

No Comments

No Known Activations