INDEX

Explanations

technical terms and jargon related to scientific or medical studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 shift

-0.46

StatusBadRequest

-0.44

след

-0.44

 Shift

-0.43

 acte

-0.43

Shift

-0.42

 Kela

-0.42

EIO

-0.42

 Maler

-0.41

をかけて

-0.41

POSITIVE LOGITS

出版年

0.91

帖最后由

0.82

 المعيارى

0.80

devamını

0.80

contentLoaded

0.80

GraphicsUnit

0.79

 Italijanski

0.79

 跳转至

0.78

 ModelExpression

0.74

évaluateur

0.74

Activations Density 2.252%

technical terms and jargon related to scientific or medical studies

No Comments

No Known Activations