INDEX

Explanations

years and locations mentioned in a professional context

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>

-2.36

<?

-0.81

ByVersion

-0.80

 &___

-0.74

Configurer

-0.70

RuleContext

-0.69

AddWithValue

-0.69

endregion

-0.68

汉

-0.68

/**

-0.68

POSITIVE LOGITS

 madonna

1.94

 affor

1.78

 snoopy

1.73

 Abbé

1.73

 reluct

1.73

 shenan

1.69

 milf

1.68

 stockholm

1.68

 accla

1.67

 perfet

1.66

Activations Density 0.580%

years and locations mentioned in a professional context

No Comments

No Known Activations