INDEX

Explanations

references to online bots and spam-related content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 StatefulWidget

-0.47

 resourceCulture

-0.46

reactstrap

-0.43

 councils

-0.41

jalá

-0.41

 surla

-0.40

Filmographie

-0.39

setSelection

-0.39

Vu

-0.38

Източници

-0.38

POSITIVE LOGITS

 bots

0.82

bot

0.81

bots

0.71

bot

0.71

 Bots

0.68

Bot

0.68

Bots

0.68

Bot

0.64

 spamming

0.60

BOT

0.58

Activations Density 0.363%

references to online bots and spam-related content

No Comments

No Known Activations