INDEX

Explanations

references to software or technology products

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

verifyException

-0.66

 незавершена

-0.63

enumi

-0.57

 Numerade

-0.56

 للاسماء

-0.52

 pinulongan

-0.51

ToAction

-0.48

CascadeType

-0.47

Hochspringen

-0.47

unteer

-0.46

POSITIVE LOGITS

 שוליים

0.52

Sklici

0.50

Зноскі

0.47

 restTemplate

0.44

]');

0.44

sockfd

0.43

 voeren

0.42

={};

0.42

 ioutil

0.40

Lähteet

0.40

Activations Density 0.633%

references to software or technology products

No Comments

No Known Activations