INDEX

Explanations

specific product features and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

كذا

-0.43

 DbSet

-0.43

AllAfrica

-0.43

car

-0.42

 kendaraan

-0.41

 human

-0.39

 sind

-0.39

ges

-0.38

di

-0.38

setPreferred

-0.38

POSITIVE LOGITS

built

0.77

 itſelf

0.72

MemoryWarning

0.69

 متعلقه

0.69

 Référence

0.68

 myſelf

0.67

 upgraded

0.66

 refurbished

0.66

 Built

0.66

ništvo

0.65

Activations Density 0.445%

specific product features and specifications

No Comments

No Known Activations