INDEX

Explanations

items lost and found, including descriptions of lost objects and their discoverers' actions

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>

-3.18

ⓧ

-0.93

-0.88

/***

-0.84

/**

-0.83

<?

-0.77

Autoritní

-0.73

 Italijani

-0.70

 disbur

-0.65

//---

-0.63

POSITIVE LOGITS

 âgé

0.72

 expérimentés

0.72

 chargés

0.71

 spécialisé

0.68

 héri

0.68

 pisang

0.68

>\<

0.68

Juf

0.67

 kuah

0.67

 titulaire

0.66

Activations Density 2.392%

items lost and found, including descriptions of lost objects and their discoverers' actions

No Comments

No Known Activations