INDEX

Explanations

mathematical expressions and notation related to statistical estimation and modeling

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

 propOrder

-0.38

writeFieldEnd

-0.34

rawDesc

-0.34

➯

-0.33

 pstmt

-0.32

Тарихы

-0.30

 tố

-0.30

 σύ

-0.30

義

-0.29

GEBURTS

-0.28

POSITIVE LOGITS

 individual

0.60

Individual

0.59

 Individual

0.57

DockStyle

0.56

RTHOOK

0.55

 EconPapers

0.55

 INDIVIDUAL

0.54

 individu

0.54

ChildScrollView

0.53

 unknownFields

0.50

Activations Density 1.052%

mathematical expressions and notation related to statistical estimation and modeling

No Comments

No Known Activations