INDEX

Explanations

appreciation and positive comments

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>

-2.99

ⓧ

-1.03

/***

-1.00

/*!

-0.83

<?

-0.81

 endow

-0.73

/**

-0.71

///**

-0.71

/**

-0.68

POSITIVE LOGITS

 lele

0.94

 Minang

0.91

 saar

0.90

Definitely

0.88

 Definitely

0.87

 territo

0.87

 bandung

0.84

 thuy

0.83

tawan

0.83

 ados

0.82

Activations Density 0.140%

appreciation and positive comments

No Comments

No Known Activations