INDEX

Explanations

references to a sequence or collection of items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

сылкі

-0.76

CloseOperation

-0.70

itects

-0.68

AnchorTagHelper

-0.67

🏻

-0.65

脚注の使い方

-0.65

IntoConstraints

-0.64

ArrowToggle

-0.63

regalo

-0.62

IsPostBack

-0.61

POSITIVE LOGITS

 Series

1.09

Series

1.05

 series

1.03

 SERIES

1.00

iseries

0.92

SERIES

0.88

series

0.85

eries

0.83

Serie

0.75

 Série

0.75

Activations Density 0.043%

references to a sequence or collection of items or concepts

No Comments

No Known Activations