INDEX

Explanations

occurrences of the word "My" or variations of it in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

-1.52

 Houſe

-1.35

Efq

-1.33

 themſelves

-1.32

 Monfieur

-1.32

 ―――――

-1.28

 Reſ

-1.25

 raiſ

-1.25

 pleaſure

-1.20

 Anſ

-1.19

POSITIVE LOGITS

my

2.33

My

2.18

my

1.99

My

1.97

MY

1.80

MY

1.49

getMy

1.41

我的

1.40

1.30

 我的

1.26

Activations Density 0.079%

occurrences of the word "My" or variations of it in the text

No Comments

No Known Activations