INDEX

Explanations

terms related to specific techniques or methods used in various fields, especially in the context of hardware or tool applications

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>

-3.64

/***

-0.95

-0.80

ⓧ

-0.80

/*!

-0.75

<?

-0.73

/**

-0.69

/*++

-0.69

<?

-0.67

///**

-0.64

POSITIVE LOGITS

 Minang

1.33

 bandung

1.25

 pymysql

1.25

 lele

1.23

 maroc

1.19

 saar

1.19

vne

1.17

 technique

1.15

 Technique

1.15

 levis

1.14

Activations Density 0.050%

terms related to specific techniques or methods used in various fields, especially in the context of hardware or tool applications

No Comments

No Known Activations