INDEX

Explanations

technical information related to gadgets and technology

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>

-2.59

/**

-0.79

<?

-0.73

-0.72

ⓧ

-0.71

rália

-0.69

/*

-0.68

<?

-0.62

 AssemblyCompany

-0.60

bolista

-0.58

POSITIVE LOGITS

 maneu

1.78

 impra

1.65

 reluct

1.59

 affor

1.59

 accla

1.58

 increa

1.57

 shenan

1.54

 practition

1.53

 disagre

1.50

 unspeak

1.45

Activations Density 1.769%

technical information related to gadgets and technology

No Comments

No Known Activations