INDEX

Explanations

book titles or chapters in a structured format

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 despotism

-1.39

 belliger

-1.35

 massacres

-1.33

 ruinous

-1.25

 Fascism

-1.25

 nukes

-1.21

 traitors

-1.20

 demoral

-1.19

 treachery

-1.17

 ineffectual

-1.14

POSITIVE LOGITS

<bos>

17.34

expandindo

2.86

GEBURTSDATUM

2.84

 betweenstory

2.79

 Administrativna

2.69

تقاوى

2.67

Autoritní

2.65

 Italijani

2.50

 Италијани

2.50

 Мексичка

2.42

Activations Density 0.958%

book titles or chapters in a structured format

No Comments

No Known Activations