INDEX

Explanations

structured data definitions and attributes in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 potencia

-0.47

ReferenceEquals

-0.46

 lähe

-0.45

 belli

-0.44

 yaşad

-0.44

 nær

-0.44

 suspendu

-0.43

 közül

-0.43

 pattes

-0.43

ServiceException

-0.43

POSITIVE LOGITS

 defaultValue

0.72

 виправивши

0.68

 default

0.68

 consultato

0.67

defaultValue

0.62

 كومونز

0.61

脚注の使い方

0.61

GIH

0.59

 Baillargeon

0.59

 minn

0.59

Activations Density 0.475%

structured data definitions and attributes in a coding context

No Comments

No Known Activations