INDEX

Explanations

phrases related to controversy or conflict, particularly around online harassment

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

 hairc

-1.37

fuf

-1.36

 scrat

-1.30

 increa

-1.28

 sappi

-1.27

 guarante

-1.27

 chrysler

-1.25

 emphat

-1.24

 unve

-1.24

 maneu

-1.23

POSITIVE LOGITS

 Instead

0.85

 They

0.84

 Specifically

0.75

 ***!

0.74

 Firstly

0.71

They

0.70

He

0.70

 After

0.69

])):

0.69

Instead

0.69

Activations Density 0.596%

phrases related to controversy or conflict, particularly around online harassment

No Comments

No Known Activations