INDEX

Explanations

news-related entities and terms like names, dates, and television networks

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>

-1.14

 Cataluña

-0.59

Mə

-0.53

fe

-0.51

Fe

-0.50

 Levin

-0.50

 Ying

-0.50

 pleg

-0.50

ধ্য

-0.49

insee

-0.49

POSITIVE LOGITS

ftu

1.00

 maneu

0.97

 Février

0.96

 bangkok

0.94

 quran

0.90

 squa

0.89

 wien

0.88

 lara

0.88

kyo

0.87

 reft

0.87

Activations Density 0.735%

news-related entities and terms like names, dates, and television networks

No Comments

No Known Activations