INDEX

Explanations

instances of the word "go" and its variations, indicating movement or action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

 становника

-0.45

IVEREF

-0.43

Personendaten

-0.43

 OFDb

-0.43

bcryptjs

-0.42

ConverterFactory

-0.41

 समीक्षाओं

-0.41

GEBURTSDATUM

-0.40

CDCl

-0.40

genöss

-0.40

POSITIVE LOGITS

 ahead

0.69

ahead

0.60

Go

0.57

ofed

0.54

 avanti

0.54

 Ahead

0.54

Go

0.53

Ahead

0.53

bble

0.51

 AHEAD

0.51

Activations Density 0.100%

instances of the word "go" and its variations, indicating movement or action

No Comments

No Known Activations