INDEX

Explanations

expressions of hope and encouragement directed at others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

InstrumentedTest

-0.59

UrlResolution

-0.52

 (;;)

-0.52

 referenties

-0.50

 soddis

-0.49

 سكانية

-0.48

JpaRepository

-0.48

といけない

-0.46

userdetails

-0.43

hosa

-0.43

POSITIVE LOGITS

 yours

1.21

yours

0.83

 yourselves

0.83

 Yours

0.81

 YOUR

0.79

your

0.75

 vôtre

0.73

 your

0.70

 theirs

0.70

 YOURSELF

0.69

Activations Density 0.214%

expressions of hope and encouragement directed at others

No Comments

No Known Activations

expressions of hope and encouragement directed at others

No Comments

No Known Activations