INDEX

Explanations

elements related to quotations or dialogue in text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

[];

-0.59

 tangga

-0.57

etheless

-0.56

zuführen

-0.56

 zufolge

-0.55

 OMITTED

-0.55

transQ

-0.54

 Winaray

-0.54

HomeAsUpEnabled

-0.53

})));

-0.52

POSITIVE LOGITS

Rüyada

0.56

richTextPanel

0.55

Lur

0.54

OrBuilder

0.53

 resourceCulture

0.51

Resol

0.50

hoeddwyd

0.50

 الرياضيه

0.50

NewUrlParser

0.49

 MutableLiveData

0.49

Activations Density 0.087%

elements related to quotations or dialogue in text

No Comments

No Known Activations