INDEX

Explanations

technical terms or code related to programming and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 الدولى

-0.62

 estekak

-0.54

 informée

-0.53

.*")]

-0.51

 casó

-0.49

esez

-0.48

 Allah

-0.48

"/>

-0.44

audiovisuel

-0.44

"]

-0.44

POSITIVE LOGITS

 autorytatywna

0.88

ArgsConstructor

0.77

PropertyChanging

0.67

 pinulongan

0.66

 CoreData

0.64

EndContext

0.62

Personendaten

0.61

CopyWith

0.59

DBNull

0.59

BeforeEach

0.58

Activations Density 7.961%

technical terms or code related to programming and functions

No Comments

No Known Activations