INDEX

Explanations

terms related to scientific inquiry and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 وتسجيلات

-0.64

+#+

-0.56

DeleteBehavior

-0.55

-0.54

IsContent

-0.53

sivity

-0.53

photobucket

-0.53

]');

-0.51

triques

-0.51

︎

-0.50

POSITIVE LOGITS

énario

0.64

の場合

0.63

 BoxFit

0.60

ledem

0.57

の場合は

0.56

に限

0.56

AsUp

0.49

 generally

0.49

 tends

0.48

 meeste

0.48

Activations Density 0.955%

terms related to scientific inquiry and methodologies

No Comments

No Known Activations