INDEX

Explanations

patterns related to structured data identifiers

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

 مرئيه

-0.52

 OFDb

-0.47

setcounter

-0.47

__":

-0.47

󠁣

-0.47

orsese

-0.46

 kaynağından

-0.42

 autorytatywna

-0.42

Personensuche

-0.40

 GenerationType

-0.40

POSITIVE LOGITS

Trans

0.43

titleMargin

0.42

 Schna

0.42

gemä

0.41

 continúa

0.41

Play

0.40

GeneratedCode

0.40

 titolata

0.39

 Play

0.38

 expresa

0.38

Activations Density 0.353%

patterns related to structured data identifiers

No Comments

No Known Activations