INDEX

Explanations

words and forms related to the prefix "En-" indicating an action of causing or making something happen

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 AssemblyCulture

-0.98

extAlignment

-0.93

fucker

-0.91

LSB

-0.89

Viki

-0.86

astify

-0.84

 ujednoznacz

-0.81

tzmann

-0.80

GIP

-0.79

 Theodo

-0.79

POSITIVE LOGITS

En

1.57

en

1.57

EN

1.48

En

1.36

 Ennis

1.28

 Enid

1.19

 Enfield

0.97

 Эн

0.93

en

0.92

 encephal

0.92

Activations Density 0.072%

words and forms related to the prefix "En-" indicating an action of causing or making something happen

No Comments

No Known Activations