INDEX

Explanations

mentions of negative sentiments or controversy, such as displeasure and buzz surrounding a topic

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>

-2.72

ⓧ

-0.77

<?

-0.76

/***

-0.75

-0.73

/*

-0.64

//{

-0.63

/**

-0.58

<?

-0.57

 deliver

-0.57

POSITIVE LOGITS

 Khart

1.41

Juf

1.34

 fortn

1.27

 Keny

1.26

 unce

1.23

 secon

1.22

 Muhamma

1.19

 Minang

1.18

 Sarm

1.18

 inext

1.17

Activations Density 1.786%

mentions of negative sentiments or controversy, such as displeasure and buzz surrounding a topic

No Comments

No Known Activations