INDEX

Explanations

dates and locations in news articles

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

Negative Logits

<bos>

-2.83

/**

-1.19

<?

-1.14

-1.01

ⓧ

-0.96

/***

-0.83

/*

-0.78

<?

-0.73

/*!

-0.69

-0.61

POSITIVE LOGITS

 seksi

0.82

 Karang

0.79

 Pekan

0.77

 Jambi

0.75

 catég

0.73

 Palembang

0.73

 Minang

0.72

 Meksi

0.72

 optik

0.69

 Hitam

0.69

Activations Density 0.161%

dates and locations in news articles

No Known Activations