INDEX

Explanations

numbers and their related statistical representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

SourceChecksum

-0.49

uchin

-0.42

上

-0.40

begin

-0.39

DialogContent

-0.39

Underline

-0.38

 océ

-0.38

 zakon

-0.38

ודם

-0.37

 utafitiHapana

-0.37

POSITIVE LOGITS

ArrowToggle

0.80

 initComponents

0.75

*/;

0.75

windowFixed

0.71

 kasarigan

0.70

 تانيه

0.69

μβρίου

0.69

MemoryWarning

0.68

WriteTagHelper

0.66

########.

0.65

Activations Density 2.305%

numbers and their related statistical representations

No Comments

No Known Activations