INDEX

Explanations

terms related to educational content and public inquiries

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.74

<?

-1.06

-1.00

ⓧ

-0.92

/***

-0.85

<?

-0.83

/**

-0.79

<!--

-0.75

/*!

-0.74

Dá

-0.74

POSITIVE LOGITS

 unce

1.55

 squa

1.54

 inext

1.50

 secon

1.43

 sovere

1.40

 unwarran

1.35

 Shakspeare

1.35

 unlaw

1.30

 paradiso

1.30

 oleo

1.29

Activations Density 1.684%

terms related to educational content and public inquiries

No Comments

No Known Activations