INDEX

Explanations

terms related to statistics and data representation

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

nościo

-0.83

AndEndTag

-0.77

ValueGeneration

-0.72

ReusableCell

-0.65

 resourceCulture

-0.61

 patrie

-0.59

LinkId

-0.58

 škoda

-0.55

ETYPE

-0.54

脚注の使い方

-0.54

POSITIVE LOGITS

تقاوى

0.63

født

0.61

OGND

0.53

QtCore

0.50

 Meksiku

0.49

=?,

0.49

lau

0.49

TestBed

0.48

?»

0.47

»?

0.47

Activations Density 1.069%

terms related to statistics and data representation

No Comments

No Known Activations