INDEX

Explanations

phrases expressing intentions or desires to perform actions

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

般

-0.52

to

-0.52

ruik

-0.51

 total

-0.50

 arah

-0.49

 tribu

-0.49

fseek

-0.48

 đàn

-0.48

载

-0.48

 internetowa

-0.47

POSITIVE LOGITS

WebVitals

0.80

 Audiodateien

0.75

 disambiguazione

0.72

Portail

0.69

HasForeignKey

0.68

 Physica

0.67

PickerController

0.67

 дописавши

0.66

بوابة

0.66

 Мексичка

0.66

Activations Density 0.168%

phrases expressing intentions or desires to perform actions

No Comments

No Known Activations