INDEX

Explanations

elements of code or structured data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

#+#

-0.75

 otomatig

-0.69

OGND

-0.69

Vidite

-0.68

yntaxException

-0.68

 resourceCulture

-0.68

Viited

-0.68

Искәрмәләр

-0.68

 محفوظة

-0.68

Diweddarwch

-0.65

POSITIVE LOGITS

 geisti

0.43

 męski

0.42

 zichzelf

0.40

spania

0.40

 Juifs

0.39

 especiais

0.38

 Jefus

0.38

 sociala

0.38

 leçons

0.38

 ésta

0.38

Activations Density 0.878%

elements of code or structured data

No Comments

No Known Activations