INDEX

Explanations

warnings, disclaimers, and legal information in text documents

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>

-2.26

-0.77

 quitted

-0.71

<?

-0.69

 disbur

-0.64

/*!

-0.64

ⓧ

-0.64

 alcançar

-0.61

 superintend

-0.60

<?

-0.57

POSITIVE LOGITS

igarette

0.67

 Expt

0.66

 venuto

0.65

 maroc

0.65

 tolu

0.65

 pensato

0.65

 italia

0.63

cæ

0.63

 ados

0.62

noinspection

0.61

Activations Density 0.285%

warnings, disclaimers, and legal information in text documents

No Comments

No Known Activations