INDEX

Explanations

words related to statistics and their analysis

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

 internetowa

-0.54

 AssemblyCompany

-0.48

الحياه

-0.47



-0.47

 multiple

-0.44

nelli

-0.44

 parar

-0.44

jeux

-0.44

zám

-0.44

っぱり

-0.43

POSITIVE LOGITS

 example

0.86

 يتيمه

0.81

 exemples

0.79

example

0.78

 exemplar

0.78

 ejemplo

0.78

ValueStyle

0.77

 Examples

0.76

ItemBackground

0.76

Example

0.75

Activations Density 0.666%

words related to statistics and their analysis

No Comments

No Known Activations