INDEX

Explanations

prepositions followed by nouns indicating a connection or an action

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>

-3.66

ⓧ

-0.73

<?

-0.70

/**

-0.64

///**

-0.64

-0.63

SystemColors

-0.62

IsRequired

-0.62

var

-0.61

public

-0.61

POSITIVE LOGITS

 wien

1.70

 stockholm

1.67

 maneu

1.61

 riviera

1.61

 affor

1.60

 eiffel

1.59

 lidl

1.57

 increa

1.53

Juf

1.53

 squa

1.52

Activations Density 0.940%

prepositions followed by nouns indicating a connection or an action

No Comments

No Known Activations