INDEX

Explanations

mentions of wars and military conflicts

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

<bos>

-0.62

ConstraintMaker

-0.51

狸

-0.50

秩

-0.50

刺客

-0.50

茅

-0.48

称号

-0.48

 huelga

-0.48

 nakalista

-0.48

nev

-0.47

POSITIVE LOGITS

 swarovski

1.26

 hairc

1.25

war

1.21

 Darío

1.18

WAR

1.16

 unwarran

1.14

 unlaw

1.14

 nutella

1.13

War

1.11

War

1.11

Activations Density 0.091%

mentions of wars and military conflicts

No Comments

No Known Activations