INDEX

Explanations

occurrences of the word "my" in different contexts, often related to personal ownership or reference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 BorderSide

-0.92

IsContent

-0.81

Datuak

-0.78

 ThemeData

-0.77

addGap

-0.74

IUrlHelper

-0.72

NSIndexPath

-0.71

帖最后由

-0.69

ConstraintMaker

-0.68

testens

-0.67

POSITIVE LOGITS

my

1.83

My

1.59

My

1.37

MY

1.33

MY

1.05

getMy

1.00

Мой

0.97

mys

0.91

my

0.90

 Мой

0.82

Activations Density 0.118%

occurrences of the word "my" in different contexts, often related to personal ownership or reference

No Comments

No Known Activations