INDEX

Explanations

mathematical terminology and notation related to statistical functions and expressions

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

‬

-0.42

CPR

-0.39

 marketable

-0.37

anco

-0.37

 isNameExpr

-0.35

Hn

-0.35

 عص

-0.35

∠

-0.35

Mil

-0.35

خش

-0.35

POSITIVE LOGITS

 Bewußt

0.64

 Vordergrund

0.55

 Gedanke

0.54

 tričko

0.52

jenige

0.51

 desmotivaciones

0.50

 geométrico

0.50

 Italij

0.50

 Einfluß

0.49

jenigen

0.48

Activations Density 3.514%

mathematical terminology and notation related to statistical functions and expressions

No Comments

No Known Activations