INDEX

Explanations

variations of the word "form" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

NCC

-0.81

 Keegan

-0.81

 Cáceres

-0.76

wyczaj

-0.76

()]

-0.74

 Honig

-0.73

lihood

-0.71

 Chapitre

-0.71

 arbitrage

-0.70

"])

-0.70

POSITIVE LOGITS

 FORM

1.51

 Form

1.33

 Forms

1.30

FORM

1.28

form

1.26

Form

1.26

 Forma

1.21

 FORMS

1.20

 form

1.16

 forms

1.15

Activations Density 0.132%

variations of the word "form" in different contexts

No Comments

No Known Activations