INDEX

Explanations

technical terms related to scientific analysis or algorithms

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

 onAnimation

-0.61

liothèque

-0.60

🏻‍♀️

-0.57

CROSSTALK

-0.55

othesis

-0.55

 vantagem

-0.54

 accesibles

-0.54

UALA

-0.53

 supérieures

-0.53

XmlIgnore

-0.52

POSITIVE LOGITS

 EconPapers

0.85

IndentedString

0.68

ंदीखरीदारी

0.68

Tembelea

0.67

DoubleQuotes

0.62

 pinulongan

0.62

évaluateur

0.59

Décès

0.59

تقاوى

0.59

__(/*!

0.58

Activations Density 0.935%

technical terms related to scientific analysis or algorithms

No Comments

No Known Activations