INDEX

Explanations

specific numerical addresses or identifiers in a data structure

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

 للمعارف

-0.58

 excit

-0.54

 Plin

-0.50

 liquids

-0.48

 Periodicals

-0.47

badlogic

-0.46

 Grossman

-0.46

 ideje

-0.46

Muta

-0.45

 Agua

-0.45

POSITIVE LOGITS

ellido

0.71

MutableLiveData

0.66

principalTable

0.63

AnchorStyles

0.61

 الرياضيه

0.60

 ویکی‌پدیا

0.58

าศ

0.56

Parabéns

0.54

っこう

0.54

*)((

0.54

Activations Density 0.005%

specific numerical addresses or identifiers in a data structure

No Comments

No Known Activations