INDEX

Explanations

phrases related to technical specifications or instructions within a document, with focus on terms like "extending lengthwise" or "positioned between."

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>

-2.46

ScopeManager

-0.80

-0.78

ⓧ

-0.74

<?

-0.71

Autoritní

-0.68

InvalidProtocol

-0.68

Enllaços

-0.68

writeFieldEnd

-0.68

Демографія

-0.67

POSITIVE LOGITS

 maroc

1.49

 milano

1.41

 bandung

1.39

 wien

1.35

 stockholm

1.32

 pollut

1.31

 embodi

1.28

 jaya

1.27

 ricardo

1.27

 ananas

1.27

Activations Density 0.400%

phrases related to technical specifications or instructions within a document, with focus on terms like "extending lengthwise" or "positioned between."

No Comments

No Known Activations