INDEX

Explanations

locations within a dataset

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

ings

-0.75

úgó

-0.67

-0.65

 Dezember

-0.65

 листопада

-0.64

 Laramie

-0.63

 saad

-0.63

the

-0.63

ب

-0.62

GraphicsUnit

-0.61

POSITIVE LOGITS

Loc

1.25

loc

1.23

loc

1.17

 Locust

1.12

Loc

1.06

locs

0.93

 Locator

0.93

calaure

0.91

MLLoader

0.91

 locust

0.89

Activations Density 0.003%

locations within a dataset

No Comments

No Known Activations

locations within a dataset

No Comments

No Known Activations