INDEX

Explanations

the beginning of sentences or paragraphs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.12.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reluct

-2.60

 unlaw

-2.51

 disgra

-2.46

 impra

-2.39

 disagre

-2.35

 unspeak

-2.35

 impractica

-2.32

 increa

-2.26

Juf

-2.24

 unwarran

-2.18

POSITIVE LOGITS

<bos>

13.29

Autoritní

2.21

 Administrativna

2.15

 betweenstory

2.01

expandindo

2.00

تقاوى

2.00

GEBURTSDATUM

1.95

 Italijani

1.90

 Мексичка

1.88

 kasarigan

1.80

Activations Density 0.910%

the beginning of sentences or paragraphs

No Comments

No Known Activations