INDEX

Explanations

comparative terms and phrases related to preferences or options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

 officially

-0.39

紆

-0.36

曖昧さ回避

-0.35

 pères

-0.34

ardon

-0.34

startdate

-0.34

 táctil

-0.33

inv

-0.33

CLAS

-0.33

끔

-0.32

POSITIVE LOGITS

Попис

0.66

 незавершена

0.60

BeginContext

0.59

Jeografia

0.54

msgTypes

0.50

isContained

0.50

GEBURTSDATUM

0.50

хьтан

0.49

Personensuche

0.49

 فريبيس

0.48

Activations Density 0.955%

comparative terms and phrases related to preferences or options

No Comments

No Known Activations