INDEX

Explanations

structured data and hierarchical formats in various contexts

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

 Administrativna

-0.52

 MatDialog

-0.51

OrNil

-0.47

OGND

-0.44

pointments

-0.44

enemies

-0.44

sectors

-0.43

 FBref

-0.43

exels

-0.43

來說

-0.42

POSITIVE LOGITS

 lenker

0.43

ApiProperty

0.35

ServletException

0.34

 secundario

0.34

FormTagHelper

0.34

 Smaller

0.33

 تنا

0.33

دانشنامهٔ

0.32

Smaller

0.32

 <<<<<<<<<<<<<<

0.31

Activations Density 0.663%

structured data and hierarchical formats in various contexts

No Comments

No Known Activations