INDEX

Explanations

references to programming libraries or frameworks, specifically those involving collections

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

 دیکھیے

-0.72

 विश्वसनीयता

-0.64

zeba

-0.63

 nakalista

-0.61

 pinulongan

-0.60

 Saddam

-0.59

 nonUne

-0.59

Abitanti

-0.58

SourceChecksum

-0.58

penup

-0.57

POSITIVE LOGITS

 AssemblyCulture

0.57

Datuak

0.52

KommentareTeilen

0.51

OrNil

0.51

 AssemblyCompany

0.50

 الحره

0.49

Viitteet

0.48

 venons

0.47

printStackTrace

0.47

 pratiquer

0.47

Activations Density 0.007%

references to programming libraries or frameworks, specifically those involving collections

No Comments

No Known Activations