INDEX

Explanations

sections of text containing information about documents or studies being referenced

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

показания

-0.57

 MenuView

-0.56

merking

-0.55

يميديا

-0.54

rrggbb

-0.54

anskje

-0.54

 initComponents

-0.54

 الرياضيه

-0.53

 jScrollPane

-0.53

__":

-0.52

POSITIVE LOGITS

 íntegra

0.52

 original

0.51

 Ceinture

0.51

 Detention

0.51

 verbatim

0.48

 details

0.48

FULL

0.47

原始

0.47

 détail

0.47

asinya

0.47

Activations Density 0.873%

sections of text containing information about documents or studies being referenced

No Comments

No Known Activations