INDEX

Explanations

references to defined categories or classifications within a given context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Team

-0.61

 Team

-0.59

team

-0.56

 المعيارى

-0.55

Réalisation

-0.54

 للاسماء

-0.54

 Piran

-0.50

ynomial

-0.49

LookAnd

-0.49

eve

-0.47

POSITIVE LOGITS

 groups

0.86

Datuak

0.84

 groupes

0.83

 geslacht

0.77

 gruppi

0.75

허

0.75

below

0.73

 grupo

0.72

 grupos

0.72

 groupe

0.70

Activations Density 0.167%

references to defined categories or classifications within a given context

No Comments

No Known Activations

references to defined categories or classifications within a given context

No Comments

No Known Activations