INDEX

Explanations

mathematical notation or expressions related to functions and polynomials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

SharedCtor

-0.68

 queſta

-0.66

脚注の使い方

-0.64

 EconPapers

-0.64



-0.63

 nahilalakip

-0.62

 propOrder

-0.62

 كومونز

-0.61

 تانيه

-0.59

 Waſſer

-0.58

POSITIVE LOGITS

cop

0.33

 Acker

0.30

Ph

0.30

 ahead

0.29

--)

0.29

印

0.28

Wh

0.28

 central

0.28

rep

0.27

Lu

0.27

Activations Density 0.433%

mathematical notation or expressions related to functions and polynomials

No Comments

No Known Activations