INDEX

Explanations

the preposition "for."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

TagMode

-0.54

 bitte

-0.40

ंदु

-0.38

 kids

-0.38

kid

-0.36

 temporary

-0.35

 civils

-0.35

hopefully

-0.35

封

-0.34

いよいよ

-0.34

POSITIVE LOGITS

 terkenal

0.63

 reputations

0.62

 famous

0.62

Famous

0.60

 Famous

0.60

 känd

0.59

famous

0.59

 שוליים

0.58

 surla

0.58

 مشين

0.57

Activations Density 0.486%

the preposition "for."

No Comments

No Known Activations