INDEX

Explanations

details related to calibration and measurement parameters in data models

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 estimés

-0.46

GenerationType

-0.45

 stands

-0.45

tara

-0.45

vart

-0.45

simpleType

-0.45

 internal

-0.44

aturing

-0.44

geten

-0.44

 knock

-0.44

POSITIVE LOGITS

LLocation

0.83

windowFixed

0.71

хьтан

0.65

data

0.63

tonsoft

0.63

ioutil

0.61

données

0.61

้อมูล

0.61

evidence

0.59

 data

0.59

Activations Density 1.163%

details related to calibration and measurement parameters in data models

No Comments

No Known Activations