INDEX

Explanations

descriptions of different aspects or attributes that are considered noteworthy or important

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>

-2.84

ⓧ

-0.87

/***

-0.86

<?

-0.85

/**

-0.81

-0.65

/*

-0.62

//---

-0.61

/*!

-0.60

ɵɵ

-0.59

POSITIVE LOGITS

 Minang

1.23

 lele

1.16

 vinci

1.14

 Karang

1.12

 Jambi

1.11

 seksi

1.10

vne

1.10

 maroc

1.09

 Muhamma

1.09

 tramont

1.05

Activations Density 0.247%

descriptions of different aspects or attributes that are considered noteworthy or important

No Comments

No Known Activations