INDEX

Explanations

referential identifiers and names

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

Personensuche

-0.67

featureID

-0.66

GOTREF

-0.65

principalColumn

-0.64

oneofs

-0.62

isContained

-0.60

oredCriteria

-0.57

IUrlHelper

-0.56

 nahilalakip

-0.56

rungsseite

-0.55

POSITIVE LOGITS

 michel

0.42

localPosition

0.35

 newspaper

0.35

ləş

0.35

ěř

0.34

weakSelf

0.33

gridx

0.32

Intérieur

0.32

aClass

0.31

oliber

0.31

Activations Density 0.192%

referential identifiers and names

No Comments

No Known Activations