INDEX

Explanations

references to images or visuals

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>

-2.99

ⓧ

-1.34

<?

-1.14

/*

-0.95

/**

-0.94

 springfox

-0.89

-0.88

<?

-0.73

/*++

-0.72

/***

-0.67

POSITIVE LOGITS

 emphat

1.57

 accla

1.55

 maneu

1.55

 affor

1.49

 increa

1.45

 inev

1.44

 wien

1.43

 lele

1.41

 resear

1.38

Juf

1.36

Activations Density 0.115%

references to images or visuals

No Comments

No Known Activations