INDEX

Explanations

preference-related terms/actions, particularly focusing on the concept of choosing or selecting

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.16

-0.76

public

-0.70

/*---

-0.67

JspWriter

-0.66

ⓧ

-0.66

Enlaces

-0.65

protected

-0.65

},{

-0.65

 operate

-0.64

POSITIVE LOGITS

 madonna

1.72

 milf

1.71

 stockholm

1.70

 maneu

1.67

 strick

1.63

 eiffel

1.63

 affor

1.62

 hentai

1.60

 wikihow

1.59

 scrat

1.56

Activations Density 0.081%

preference-related terms/actions, particularly focusing on the concept of choosing or selecting

No Comments

No Known Activations