INDEX

Explanations

instances of the word "in" and phrases indicating presence or inclusion

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Enth

-0.58

addCriterion

-0.57

Personensuche

-0.57

DMC

-0.56

Naissance

-0.54

ắc

-0.53

otry

-0.53

eqn

-0.52

 casting

-0.52

ombo

-0.52

POSITIVE LOGITS

تقاوى

0.52

 zví

0.49

 AttributeSet

0.48

nocache

0.47

 vPvB

0.47

 publicitaires

0.47

 člov

0.46

>",

0.46

 Banjar

0.45

/**

0.45

Activations Density 0.126%

instances of the word "in" and phrases indicating presence or inclusion

No Comments

No Known Activations