INDEX

Explanations

words related to visual technology and multimedia experiences, particularly regarding screens, projection, and video content

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>

-2.53

/**

-0.73

ⓧ

-0.64

<?

-0.63

HasIndex

-0.62

/*

-0.58

RTDA

-0.56

 help

-0.55

ValueGeneration

-0.54

POSITIVE LOGITS

 affor

1.52

 unden

1.41

 swarovski

1.39

 ecru

1.37

 hairc

1.37

 practition

1.35

Juf

1.29

 stockholm

1.27

 Manufact

1.27

 excru

1.27

Activations Density 1.043%

words related to visual technology and multimedia experiences, particularly regarding screens, projection, and video content

No Comments

No Known Activations