INDEX

Explanations

references to specific components and configurations in technical documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 houſe

-0.64

 Theſe

-0.62

 occaf

-0.61

 purpoſe

-0.61

 ſtate

-0.59

 perfons

-0.59

 Majefty

-0.58

 ſmall

-0.56

%)$

-0.56

 greateſt

-0.55

POSITIVE LOGITS

OGND

0.74

tagHelperRunner

0.73

QMetaType

0.69

GEBURTSDATUM

0.69

 للمعارف

0.68

tonode

0.68

queryInterface

0.63

الإنجليزية

0.63

 BrowserModule

0.62

 تانيه

0.61

Activations Density 0.779%

references to specific components and configurations in technical documents

No Comments

No Known Activations