INDEX

Explanations

details related to observing and analyzing data, particularly in educational settings

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>

-3.20

ⓧ

-0.80

-0.76

/***

-0.74

<?

-0.73

/*++

-0.67

/**

-0.66

Даль

-0.63

Vegeu

-0.60

protected

-0.58

POSITIVE LOGITS

 stockholm

1.67

 wien

1.56

 strick

1.54

 maneu

1.53

 secon

1.52

 increa

1.51

 affor

1.50

 effe

1.48

fta

1.48

tew

1.47

Activations Density 0.070%

details related to observing and analyzing data, particularly in educational settings

No Comments

No Known Activations