INDEX

Explanations

Japanese names and terms

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>

-2.40

/*

-0.70

-0.66

<?

-0.65

 onView

-0.60

govina

-0.60

exitRule

-0.59

 дописавши

-0.58

quine

-0.57

apnews

-0.56

POSITIVE LOGITS

 emphat

1.77

 milf

1.77

 madonna

1.76

 affor

1.69

 perfet

1.66

 maneu

1.59

 accla

1.58

 stockholm

1.57

 peppa

1.57

 inev

1.55

Activations Density 0.157%

Japanese names and terms

No Comments

No Known Activations