INDEX

Explanations

numerical values and quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

VYMaps

-0.56

 ujednoznacz

-0.54

TagMode

-0.48

 Roskov

-0.47

 Stornier

-0.47

 Bisch

-0.46

subpackage

-0.46

TestingModule

-0.46



-0.45

 defaultstate

-0.44

POSITIVE LOGITS

 Ines

0.44

اقرأ

0.43

 cauza

0.40

Rae

0.39

 ExecuteAsync

0.39

 pierdas

0.39

 Gedanke

0.38

出版年

0.38

delivery

0.37

 Anemia

0.37

Activations Density 0.903%

numerical values and quantities

No Comments

No Known Activations