INDEX

Explanations

locations and geographical references

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

占

-0.33

 Latein

-0.32

 Join

-0.32

감

-0.32

 Ajoutez

-0.31

addComponent

-0.31

 Agregar

-0.31

 Ribeiro

-0.31

 Green

-0.30

Ju

-0.29

POSITIVE LOGITS

IntoConstraints

0.77

Хьажоргаш

0.71

 kaynağından

0.68

sizeCache

0.68

tagHelperRunner

0.66

NameInMap

0.63

 فريبيس

0.62

 يتيمه

0.61

 المعرف

0.60

ContentAsync

0.59

Activations Density 0.629%

locations and geographical references

No Comments

No Known Activations