INDEX

Explanations

the name "Ryan" in the text

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>

-2.91

ⓧ

-1.07

-1.02

<?

-0.99

/**

-0.94

/***

-0.87

<?

-0.79

/*

-0.75

///**

-0.66

AutoScaleMode

-0.65

POSITIVE LOGITS

 Ryan

1.29

Ryan

1.25

 ryan

1.14

cæ

0.82

 Juillet

0.81

 pank

0.80

 saar

0.79

ryan

0.79

 silikon

0.79

 Bibl

0.79

Activations Density 0.073%

the name "Ryan" in the text

No Comments

No Known Activations