INDEX

Explanations

mathematical symbols, specifically those related to matrices and arrays

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

principalTable

-0.74

 iprot

-0.71

تقاوى

-0.69



-0.66

 Wiktionnaire

-0.66

帖最后由

-0.65

kháu

-0.64

 transférez

-0.63

Дереккөздер

-0.63

ugges

-0.63

POSITIVE LOGITS

0.87

0.54

 StatelessWidget

0.53

Kt

0.50

 lemak

0.48

 present

0.48

csi

0.47

 człowiek

0.46

യും

0.46

്‍

0.45

Activations Density 0.047%

mathematical symbols, specifically those related to matrices and arrays

No Comments

No Known Activations