INDEX

Explanations

references to items and their attributes in structured data or code

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

 GenerationType

-0.98

 Мексичка

-0.90

MemoryWarning

-0.89

PerformLayout

-0.86

EnableWeb

-0.85

 Hough

-0.82

Predecesor

-0.82

 lill

-0.82

GraphicsUnit

-0.81

]<<

-0.81

POSITIVE LOGITS

 items

1.70

 Items

1.68

 item

1.64

 ITEM

1.63

items

1.62

 Item

1.60

 ITEMS

1.57

ITEM

1.41

Items

1.41

Item

1.36

Activations Density 0.064%

references to items and their attributes in structured data or code

No Comments

No Known Activations