INDEX

Explanations

company names

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>

-2.31

/**

-1.16

/*

-1.01

ⓧ

-1.00

<?

-0.98

-0.84

-0.83

ोंने

-0.83

 saites

-0.82

uxxxx

-0.81

POSITIVE LOGITS

 philanth

1.95

 accla

1.86

 Keny

1.85

 affor

1.85

 stockholm

1.81

 unlaw

1.76

 wherea

1.75

 michelin

1.72

 practition

1.72

 sputnik

1.72

Activations Density 0.850%

company names

No Comments

No Known Activations