INDEX

Explanations

references to specific individuals and their associated merits or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

OGND

-0.59

 للمعارف

-0.59

>-->

-0.55

 ویکی‌پدیا

-0.51

matchCondition

-0.51

 TableColumn

-0.51

 Wicidata

-0.50

Ther

-0.50

Cof

-0.50

:][

-0.48

POSITIVE LOGITS

deauna

0.63

olverine

0.62

PreferredItem

0.58

wpi

0.58

 saites

0.57

MessageTagHelper

0.56

řeba

0.55

Autoritní

0.55

windowFixed

0.54

uresti

0.52

Activations Density 1.331%

references to specific individuals and their associated merits or actions

No Comments

No Known Activations