INDEX

Explanations

elements related to health and nutrition

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

char

-0.35

タレ

-0.32

็ม

-0.30

 nominal

-0.30

al

-0.30

баты

-0.30

TestBed

-0.29

setVerticalGroup

-0.29

 autor

-0.29

 تلف

-0.29

POSITIVE LOGITS

 kasarigan

0.68

تقاوى

0.60

 AssemblyProduct

0.58

 autorytatywna

0.58

 שוליים

0.58

IsMutable

0.57

parsedMessage

0.56

 vectorielle

0.56

ImageContext

0.55

engagent

0.54

Activations Density 0.721%

elements related to health and nutrition

No Comments

No Known Activations