INDEX

Explanations

references to "New Zealand," particularly when it is emphasized or in titles and headings

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.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

<bos>

-1.87

pen

-0.67

uxxxx

-0.67

<?

-0.66

CPtr

-0.64

res

-0.63

han

-0.62

 referenties

-0.62

Marshaller

-0.61

dist

-0.61

POSITIVE LOGITS

 pymysql

1.80

 maneu

1.67

 milf

1.63

 increa

1.61

 indestru

1.60

 madonna

1.58

 ricardo

1.58

 impra

1.56

 affor

1.56

 excru

1.55

Activations Density 0.335%

references to "New Zealand," particularly when it is emphasized or in titles and headings

No Comments

No Known Activations