INDEX

Explanations

questions and inquiries regarding guidance or assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

in

-0.36

 klart

-0.35

 yoktur

-0.34

 vuoden

-0.34

ponses

-0.33

as

-0.33

-0.32

働く

-0.32

 महत्व

-0.32

end

-0.32

POSITIVE LOGITS

 myſelf

0.94

CloseOperation

0.89

 initComponents

0.88

 <<<<<<<<<<<<<<

0.84

enterOuterAlt

0.83

expandindo

0.81

NewUrlParser

0.80

 actionPerformed

0.79

 nahilalakip

0.77

 AssemblyVersion

0.76

Activations Density 0.175%

questions and inquiries regarding guidance or assistance

No Comments

No Known Activations