INDEX

Explanations

the name "Horo" prominently mentioned in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ViewInit

-0.70

 Jeffries

-0.64

 snippetHide

-0.63

MigrationBuilder

-0.63

WithIdentifier

-0.62

 PICTOGRAM

-0.60

 Attach

-0.59

uminate

-0.59

 Thine

-0.59

 Paglinawan

-0.58

POSITIVE LOGITS

parsedMessage

0.73

 Division

0.73

Sub

0.71

Division

0.62

Sub

0.61

AutoField

0.58

 subset

0.57

AsUp

0.56

 kaarangay

0.55

Hor

0.55

Activations Density 0.133%

the name "Horo" prominently mentioned in various contexts

No Comments

No Known Activations