INDEX

Explanations

references to collective or inclusive pronouns signifying groups of people

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

TagHelpers

-0.73

tas

-0.70

 Palma

-0.70

境的

-0.69

 Griffith

-0.68

χ

-0.67

mat

-0.67

sin

-0.65

ꜱ

-0.65

 Leap

-0.64

POSITIVE LOGITS

everybody

1.37

everyone

1.33

 everyone

1.31

 everybody

1.30

 Everybody

1.30

Everyone

1.30

 Everyone

1.27

Everybody

1.26

 EVERYONE

1.22

 else

1.18

Activations Density 0.061%

references to collective or inclusive pronouns signifying groups of people

No Comments

No Known Activations