INDEX

Explanations

mathematical formatting and notation used in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

Билгалдахарш

-0.68

 propOrder

-0.66

 nahilalakip

-0.61

Искәрмәләр

-0.57

withIdentifier

-0.54

RTDA

-0.54

Referències

-0.54

ANTLR

-0.52

 AssemblyCompany

-0.52

OGND

-0.52

POSITIVE LOGITS

\}_{

0.45

хівовано

0.41

-------------</

0.40

ukone

0.40

éroport

0.36

 pauvreté

0.36

Toponymie

0.35

 compless

0.35

 dinosaurio

0.35

 bangunan

0.34

Activations Density 0.050%

mathematical formatting and notation used in equations

No Comments

No Known Activations