INDEX

Explanations

facts or statements emphasizing the truthfulness or accuracy of information

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>

-2.33

ⓧ

-0.89

<?

-0.84

<?

-0.80

/***

-0.78

///**

-0.77

/*

-0.72

-0.67

endwhile

-0.66

//};

-0.61

POSITIVE LOGITS

 véhic

1.09

 soulign

1.02

 récomp

0.95

 maroc

0.94

 originaire

0.94

 quoique

0.93

 fortn

0.92

Juf

0.92

 chrétien

0.91

 gettyimages

0.91

Activations Density 0.990%

facts or statements emphasizing the truthfulness or accuracy of information

No Comments

No Known Activations