INDEX

Explanations

instances of the word "my" referencing personal experiences or belongings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 itſelf

-1.69

 Houſe

-1.28

 himſelf

-1.28

 Theſe

-1.25

Efq

-1.25

 Reſ

-1.24

 themſelves

-1.23

 Monfieur

-1.21

 ―――――

-1.18

 Anſ

-1.16

POSITIVE LOGITS

My

1.64

my

1.57

My

1.35

MY

1.33

my

1.22

1.15

Me

1.13

our

1.06

MY

1.06

getMy

1.06

Activations Density 0.074%

instances of the word "my" referencing personal experiences or belongings

No Comments

No Known Activations