INDEX

Explanations

terms related to mathematical or scientific notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 wieś

-0.62

 Crowns

-0.58

κια

-0.55

 Protestantism

-0.52

 насеље

-0.50

Rov

-0.50

 sasuke

-0.50

市镇

-0.50

 Whence

-0.49

 Summa

-0.49

POSITIVE LOGITS

 فريبيس

0.82

InputBorder

0.80

 المعيارى

0.76

enumi

0.73

MLLoader

0.70

extAlignment

0.69

EndProject

0.68

0.67

AccessFile

0.67

énario

0.66

Activations Density 0.037%

terms related to mathematical or scientific notation

No Comments

No Known Activations