INDEX

Explanations

the word "designed" in various contexts

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

Portale

-0.62

 censiti

-0.60

WebVitals

-0.57

Билгалдахарш

-0.55

 acidity

-0.55

GEBURTSDATUM

-0.55

underlying

-0.54

 Ester

-0.53

tableData

-0.53

Население

-0.52

POSITIVE LOGITS

 designed

2.24

designed

2.02

 Designed

1.87

Designed

1.75

 diseñada

1.58

 diseñados

1.48

 conçue

1.48

 conçu

1.47

 diseñado

1.44

 conçus

1.40

Activations Density 0.093%

the word "designed" in various contexts

No Comments

No Known Activations