INDEX

Explanations

references to programming constructs and system-level details involving data types 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Atoi

-0.49

 JpaRepository

-0.46

شد

-0.44

downcase

-0.42

marginRight

-0.42

mensa

-0.41

 lượng

-0.40

 khoản

-0.40

Cordialement

-0.39

 sure

-0.38

POSITIVE LOGITS

Personendaten

1.06

 Вікі

0.95

 Exacts

0.90

LookAnd

0.89

 AssemblyCompany

0.88

CppMethod

0.86

bootstrapcdn

0.85

 nahilalakip

0.84

QMetaType

0.82

 EconPapers

0.80

Activations Density 0.390%

references to programming constructs and system-level details involving data types and functions

No Comments

No Known Activations