INDEX

Explanations

references to historical events, particularly related to World War II

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 inder

-0.86

 lapto

-0.83

 coö

-0.79

 ananas

-0.74

 abbra

-0.72

 pesante

-0.72

 unden

-0.72

 affez

-0.71

 Czechos

-0.71

 effe

-0.70

POSITIVE LOGITS

 Cárdenas

0.71

 WWII

0.71

avaş

0.69

 wartime

0.64

 Cár

0.62

War

0.60

war

0.60

 Lázaro

0.59

 Weltkrieg

0.59

 Darío

0.57

Activations Density 0.099%

references to historical events, particularly related to World War II

No Comments

No Known Activations