INDEX

Explanations

references to oral health and oral administration or processes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

rungsseite

-0.58

 تضيفلها

-0.57

تقاوى

-0.57

liothèque

-0.56

DEPORTES

-0.53

IFORNIA

-0.51

 CHLOR

-0.51

Muz

-0.50

 glaub

-0.50

들

-0.49

POSITIVE LOGITS

 MonoBehaviour

1.00

 oral

0.87

 virtual

0.86

 verbal

0.79

 Virtu

0.77

 virtu

0.77

 AssemblyCulture

0.77

 verbally

0.77

 simplifié

0.70

 sẻ

0.68

Activations Density 0.046%

references to oral health and oral administration or processes

No Known Activations