INDEX

Explanations

references to bins or binning in data 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

Negative Logits

abestanden

-0.93

allure

-0.92

GraphicsUnit

-0.83

 saluto

-0.83

 Autorizaciones

-0.81

segue

-0.80

 nakalista

-0.80

">//

-0.80

 contributo

-0.78

 bellas

-0.75

POSITIVE LOGITS

bin

1.57

Bin

1.43

 bins

1.41

Bin

1.26

bin

1.23

 Bins

1.20

BIN

1.17

Bins

1.14

BIN

1.05

bins

1.03

Activations Density 0.010%

references to bins or binning in data analysis

No Known Activations