INDEX

Explanations

references to controversial historical events and their narratives

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

Diweddarwch

-0.50

ThroughAttribute

-0.47

 disponibilités

-0.45

pulumi

-0.45

 nahilalakip

-0.44

EnableWeb

-0.44

 ब्रेकडाउन

-0.44

Попис

-0.43

 disambiguazione

-0.43

лтамалар

-0.43

POSITIVE LOGITS

 argument

0.41

komna

0.41

HomeAsUp

0.40

点此举报

0.40

ampiyon

0.38

 irrelevant

0.38

zonder

0.38

yonel

0.38

sopp

0.38

 argumentos

0.36

Activations Density 0.657%

references to controversial historical events and their narratives

No Comments

No Known Activations