INDEX

Explanations

technical terms and metrics related to scientific studies and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ExtendWith

-0.68

")));

-0.67

@"/

-0.67

__":

-0.66

WaitGroup

-0.65

__':

-0.65

iecie

-0.64

 متعلقه

-0.64

EndProject

-0.64

Hozzáférés

-0.61

POSITIVE LOGITS

 المعيارى

0.57

 TMPro

0.55

astify

0.54

centerY

0.51

viembre

0.51

parsedMessage

0.51

 pasaj

0.50

usepackage

0.48

ICOLON

0.48

InetAddress

0.47

Activations Density 6.486%

technical terms and metrics related to scientific studies and methodologies

No Comments

No Known Activations