INDEX

Explanations

concepts related to moral values and judgment in relationships, particularly in the context of marriage and personal beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

DockStyle

-0.86

 EconPapers

-0.69

şağı

-0.68

 समीक्षाओं

-0.68

__':

-0.65

EndInit

-0.64

Referències

-0.61

 estekak

-0.61

aarrggbb

-0.60

 TextInputType

-0.59

POSITIVE LOGITS

 ***!

0.54

 actionPerformed

0.50

>"+

0.42

Gdx

0.42

лактика

0.42

 Comunic

0.41

Sala

0.40

￡

0.40

 graden

0.39

 Poplar

0.38

Activations Density 1.012%

concepts related to moral values and judgment in relationships, particularly in the context of marriage and personal beliefs

No Comments

No Known Activations