INDEX

Explanations

mathematical notations, equations, and definitions related to statistical estimations and models

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

 kasarigan

-0.77

 يتيمه

-0.71

 pinulongan

-0.67

脚注の使い方

-0.64

دانشنامهٔ

-0.59

AddTagHelper

-0.56

 Biôgrafia

-0.53

 utafitiHapana

-0.52

StoreMessageInfo

-0.52

RenderAtEndOf

-0.52

POSITIVE LOGITS

pexpr

0.38

 itself

0.37

was

0.36

 odpo

0.33

 inderdaad

0.32

 actually

0.31

 mentioned

0.31

 being

0.31

 Picchu

0.31

 halen

0.30

Activations Density 2.888%

mathematical notations, equations, and definitions related to statistical estimations and models

No Comments

No Known Activations