INDEX

Explanations

negative contractions and verbs that indicate refusal or denial

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

:✨

-0.60

 peuples

-0.45

WebpackPlugin

-0.40

новништво

-0.39

 autorités

-0.38

 Relaciones

-0.37

 missione

-0.37

 cammin

-0.37

 kommunen

-0.36

 žem

-0.36

POSITIVE LOGITS

 Autorisations

0.52

}{@

0.52

UnusedPrivate

0.50

 disponibilités

0.50

 Autorizaciones

0.50

 nonUne

0.50

exitRule

0.49

 الرياضيه

0.49

 autorytatywna

0.46

dafx

0.45

Activations Density 0.013%

negative contractions and verbs that indicate refusal or denial

No Comments

No Known Activations