INDEX

Explanations

instances of recommendations or requests related to decisions or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Reverse

-0.43

 MonoBehaviour

-0.41

Bux

-0.41

 exalted

-0.40

 conosce

-0.39

Reverse

-0.39

равда

-0.38

amentul

-0.38

Orléans

-0.38

 Protestantism

-0.38

POSITIVE LOGITS

 متعلقه

0.78

 request

0.75

Personendaten

0.69

isContained

0.69

 requests

0.68

 requested

0.67

RegistryLite

0.66

 surla

0.66

 recommandons

0.65

niosek

0.64

Activations Density 0.299%

instances of recommendations or requests related to decisions or actions

No Comments

No Known Activations