INDEX

Explanations

various forms of structured or formatted data, often related to lists, tables, or collection of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Not in Any Lists

No Comments

Negative Logits

-1.73

-1.25

-1.23

in

-1.10

-1.09

to

-1.07

-1.03

the

-1.02

-1.01

The

-0.99

POSITIVE LOGITS

 autorytatywna

1.28

 desmotivaciones

1.27

 Paglinawan

1.24

 queſta

1.18

 Comprometido

1.14

SharedDtor

1.13

berdayakan

1.13

aarrggbb

1.10

Autoritní

1.10

 ainfi

1.09

Activations Density 1.158%

various forms of structured or formatted data, often related to lists, tables, or collection of information

No Comments

No Known Activations