INDEX

Explanations

references to looking or observing actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

éx

-0.65

twimg

-0.57

runApp

-0.56

]='\

-0.52

 BorderRadius

-0.50

 Colonia

-0.49

اقت

-0.49

aima

-0.49

 jButton

-0.49

{!!

-0.49

POSITIVE LOGITS

QMetaType

0.67

 createState

0.67

رشف

0.66

 médicale

0.58

horabuena

0.58

 deportivo

0.57

adaptiveStyles

0.57

 AssemblyCompany

0.57

Bibliograf

0.57

ollectionView

0.56

Activations Density 0.089%

references to looking or observing actions

No Comments

No Known Activations