INDEX

Explanations

specific names or terms within the text

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

providedIn

-0.54

newtheorem

-0.52

__':

-0.52

 aVar

-0.52

orit

-0.51

 الدولى

-0.47

MethodManager

-0.47

__":

-0.47

makeText

-0.47

TextUtils

-0.46

POSITIVE LOGITS

 gynhyrchwyd

0.78

 سكانية

0.74

artifactId

0.64

 TestBed

0.63

tagHelperRunner

0.62

EndInit

0.61

Tikang

0.60

oredCriteria

0.60

 ویکی‌پدیا

0.59

Datuak

0.59

Activations Density 0.162%

specific names or terms within the text

No Comments

No Known Activations

specific names or terms within the text

No Comments

No Known Activations