INDEX

Explanations

instances of the word "notation."

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

Datuak

-0.90

"?>

-0.82

jspx

-0.78

 lenker

-0.71

 transfieras

-0.69

ünkü

-0.67

뀜

-0.67

gameserver

-0.65

parseFrom

-0.63

 culturelles

-0.63

POSITIVE LOGITS

 notation

1.07

 Notation

1.02

 notations

1.00

Notation

0.85

notation

0.74

notations

0.66

ally

0.65

jà

0.61

Caj

0.60

أل

0.59

Activations Density 0.005%

instances of the word "notation."

No Comments

No Known Activations