INDEX

Explanations

enterprise-related terms

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>

-3.25

 nahilalakip

-0.65

set

-0.65

RepeatedField

-0.64

/*

-0.63

 GeoNames

-0.62

ValueGenerated

-0.62

SourceChecksum

-0.62

<?

-0.61

ⓧ

-0.61

POSITIVE LOGITS

 tupperware

1.43

 affor

1.37

 suscep

1.35

Juf

1.35

 increa

1.33

 jaya

1.32

 Intere

1.29

 maneu

1.29

 Minang

1.28

 snoopy

1.27

Activations Density 0.062%

enterprise-related terms

No Comments

No Known Activations