INDEX

Explanations

religious references and moral dilemmas

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

No obvious monosemantic explanation. Usually activates on comma in a 'comma, subject' pair at the end of the sentence

Explanation Uploaded by User

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.85

<?

-0.80

<?

-0.78

ⓧ

-0.75

-0.73

/**

-0.72

/***

-0.69

lateinit

-0.68

-0.66

💼

-0.62

POSITIVE LOGITS

 maneu

1.61

 affor

1.59

 impra

1.55

 accla

1.54

 reluct

1.54

 disagre

1.51

 disreg

1.50

 increa

1.48

 suscep

1.45

 berea

1.42

Activations Density 0.340%

religious references and moral dilemmas

No obvious monosemantic explanation. Usually activates on comma in a 'comma, subject' pair at the end of the sentence

No Comments

No Known Activations