INDEX

Explanations

references to various types of equipment

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-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Wardrobe

-0.68

 Tuttle

-0.61

ConstraintMaker

-0.59

 trekken

-0.59

 Garnish

-0.58

 valence

-0.57

Jîn

-0.56

ArrowToggle

-0.56

 kalend

-0.56

 thorax

-0.55

POSITIVE LOGITS

 equipment

1.40

Equipment

1.32

 Equipment

1.30

equipment

1.21

 EQUIPMENT

1.10

EQUIPMENT

0.92

Eq

0.89

ipment

0.87

 equipments

0.84

 itſelf

0.79

Activations Density 0.080%

references to various types of equipment

No Comments

No Known Activations