INDEX

Explanations

words related to prevention and preventive actions

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>

-2.88

-0.79

<?

-0.76

ⓧ

-0.73

<?

-0.66

/**

-0.59

class

-0.59

HasIndex

-0.58

/***

-0.58

PrintStream

-0.57

POSITIVE LOGITS

 Minang

1.41

Juf

1.38

 jaya

1.37

 saar

1.35

 lele

1.33

 Banjar

1.31

 bandung

1.30

hcm

1.30

kyo

1.29

aen

1.26

Activations Density 0.064%

words related to prevention and preventive actions

No Comments

No Known Activations