INDEX

Explanations

phrases indicating the presence of a call to action or solicitation

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>

-3.19

ⓧ

-1.06

<?

-0.98

/***

-0.88

/**

-0.88

-0.87

/*

-0.81

 disbur

-0.66

<?

-0.65

 rehabilitate

-0.64

POSITIVE LOGITS

 Someone

1.03

Someone

1.02

 someone

0.95

someone

0.92

 riva

0.85

 SOMEONE

0.84

 quæ

0.81

 jawa

0.79

 Jambi

0.79

 somebody

0.79

Activations Density 0.150%

phrases indicating the presence of a call to action or solicitation

No Comments

No Known Activations