INDEX

Explanations

references to corporate entities and their associated details

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 redacción

-0.29

Sch

-0.28

 muñ

-0.28

action

-0.28

 spécifique

-0.28

InitVars

-0.27

 moviliz

-0.27

Scrolled

-0.27

 nede

-0.27

 específico

-0.26

POSITIVE LOGITS

+#+

0.74

ValueStyle

0.72

principalTable

0.66

 للاسماء

0.63

twimg

0.63

 NavController

0.61

 purpoſe

0.61

 متحده

0.60

 poffible

0.60

Espèce

0.59

Activations Density 0.291%

references to corporate entities and their associated details

No Comments

No Known Activations