INDEX

Explanations

instances of complexity or complexity-related terms in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 ویکی‌پدی

-0.78

AsUp

-0.55

 ErrInvalid

-0.52

IndentedString

-0.49

cknowled

-0.49

acetic

-0.48

 հղումներ

-0.48

__":

-0.47

Dtor

-0.47

 metast

-0.47

POSITIVE LOGITS

principalColumn

0.46

новништво

0.44

 navideño

0.41

hyrchwyd

0.41

 AssemblyCulture

0.40

 سكانية

0.39

 colectiva

0.39

 plateado

0.39

 cromado

0.38

Lähteet

0.38

Activations Density 1.759%

instances of complexity or complexity-related terms in descriptions

No Comments

No Known Activations