INDEX

Explanations

references to lists and enumerations

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>

-2.81

<?

-1.00

ⓧ

-0.99

/**

-0.89

-0.78

lateinit

-0.73

glBind

-0.70

/*

-0.68

/***

-0.67

/*++

-0.66

POSITIVE LOGITS

 maneu

1.54

 bandung

1.51

 practition

1.50

 lele

1.49

 Minang

1.46

Juf

1.45

 resear

1.44

hcm

1.41

 accla

1.38

 increa

1.37

Activations Density 0.177%

references to lists and enumerations

No Comments

No Known Activations