INDEX

Explanations

the presence of the word "I" as an indicator of personal perspective or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 intptr

-0.89

-0.78

ReusableCell

-0.76

CEPTION

-0.72

 يتيمه

-0.71

Искәрмәләр

-0.70

UTTON

-0.68

 Ques

-0.65

 homen

-0.64

BRARY

-0.63

POSITIVE LOGITS

2.71

2.08

My

1.26

We

1.25

Tôi

1.20

我

1.10

ฉัน

1.07

My

1.05

tôi

1.04

We

1.00

Activations Density 0.078%

the presence of the word "I" as an indicator of personal perspective or statements

No Comments

No Known Activations