INDEX

Explanations

names of individuals and specific locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.76

ⓧ

-0.89

/**

-0.87

šech

-0.85

-0.77

<?

-0.73

/***

-0.71

USTAIN

-0.70

contentLoaded

-0.62

portál

-0.62

POSITIVE LOGITS

 Minang

1.04

 Jambi

0.99

 Palembang

0.94

 Khart

0.94

Juf

0.91

 soggior

0.91

 Banjar

0.90

 Karang

0.89

 allarg

0.89

 Keny

0.87

Activations Density 2.695%

names of individuals and specific locations

No Comments

No Known Activations