INDEX

Explanations

the term "Grand" in various contexts, indicating a focus on locations or concepts associated with grandeur

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

queryInterface

-0.62

 Verf

-0.54

 face

-0.54

 Face

-0.53

jsxFileName

-0.52

Face

-0.52

grow

-0.51

 resourceCulture

-0.51

scryfall

-0.51

>--}}

-0.51

POSITIVE LOGITS

mothers

0.73

parents

0.68

 prix

0.67

daddy

0.66

 larceny

0.64

iose

0.64

 Theft

0.63

addy

0.62

fathers

0.62

parent

0.62

Activations Density 0.138%

the term "Grand" in various contexts, indicating a focus on locations or concepts associated with grandeur

No Comments

No Known Activations