INDEX

Explanations

references to authors and their associated works or studies in scientific literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 समीक्षाओं

-0.68

Autoritní

-0.68

 kaarangay

-0.65

afficheront

-0.61

SharedDtor

-0.56

+#+#

-0.56

 للمعارف

-0.56

xically

-0.55

 Chwiliwch

-0.55

astéroïdes

-0.54

POSITIVE LOGITS

Cal

0.41

Cla

0.40

ls

0.40

Cla

0.39

MA

0.39

<eos>

0.39

Pla

0.39

MAR

0.38

PD

0.38

 President

0.38

Activations Density 0.083%

references to authors and their associated works or studies in scientific literature

No Comments

No Known Activations