INDEX

Explanations

language used in scientific or medical research, especially words and phrases related to studies, potential biases, statistical analysis, and limitations.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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

<?

-0.62

pology

-0.60

igerung

-0.58

LabelTagHelper

-0.57

ésultat

-0.56

 legible

-0.55

TagHelper

-0.54

 visibly

-0.53

 delinquency

-0.53

voked

-0.52

POSITIVE LOGITS

MockBean

0.71

 adanya

0.69

 confounding

0.66

 biais

0.65

 inaccuracies

0.63

 Biôgrafia

0.61

 inaccurate

0.58

 différences

0.58

 confound

0.57

 biases

0.57

Activations Density 3.110%

language used in scientific or medical research, especially words and phrases related to studies, potential biases, statistical analysis, and limitations.

No Comments

No Known Activations