INDEX

Explanations

mathematical expressions and variables used in scientific or technical contexts

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

cipar

-0.77

AsUp

-0.71

 nahilalakip

-0.65

انجليز

-0.64

greSQL

-0.63

 BoxFit

-0.62

invokeLater

-0.61

 arşivlendi

-0.61

braith

-0.61

utenants

-0.60

POSITIVE LOGITS

 cauſe

0.64

 ſtand

0.63

 himſelf

0.55

avaient

0.54

transQ

0.53

 caufe

0.52

 reaſon

0.52

Ữ

0.51

 againſt

0.50

しかったです

0.50

Activations Density 1.086%

mathematical expressions and variables used in scientific or technical contexts

No Comments

No Known Activations