INDEX

Explanations

references to various types of data and its collection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 colgante

-0.35

 titulado

-0.35

 pegatina

-0.34

 titulada

-0.33

 druh

-0.33

 acepción

-0.32

 inauguración

-0.32

 tercera

-0.31

 pierna

-0.31

ningss

-0.31

POSITIVE LOGITS

 data

1.55

 Data

1.23

 DATA

1.03

 데이터

0.99

 Daten

0.91

 userData

0.90

データ

0.89

数据

0.87

data

0.86

 metadata

0.85

Activations Density 0.198%

references to various types of data and its collection

No Comments

No Known Activations

references to various types of data and its collection

No Comments

No Known Activations