INDEX

Explanations

mentions of announcements, launches, and releases

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>

-2.32

ⓧ

-1.18

/**

-0.87

<?

-0.70

/*

-0.66

<?

-0.66

CopyWith

-0.63

RuleContext

-0.61

/*++

-0.60

POSITIVE LOGITS

 Minang

1.51

 Keny

1.40

 Khart

1.34

 Jambi

1.31

Juf

1.30

 maneu

1.25

 Pekan

1.23

 Karang

1.21

 Muhamma

1.19

 accla

1.18

Activations Density 3.190%

mentions of announcements, launches, and releases

No Comments

No Known Activations