INDEX

Explanations

structured data elements and references to corporate actions or recalls

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

Personendaten

-0.46

 dévelo

-0.44

 Polsek

-0.43

 كورة

-0.42

 quelcon

-0.42

aktery

-0.40

 postales

-0.40

esterno

-0.39

 numériques

-0.38

POSITIVE LOGITS

 imported

0.81

 Imported

0.78

 importing

0.78

 importer

0.76

 import

0.75

 importers

0.73

 importation

0.73

 Importing

0.71

 imports

0.70

Imported

0.68

Activations Density 0.319%

structured data elements and references to corporate actions or recalls

No Comments

No Known Activations