INDEX

Explanations

scientific terms related to numerical data analysis and properties

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

an

-0.47

 post

-0.46

-0.44

 long

-0.44

 sockaddr

-0.43

紀

-0.41

-0.40

<b>

-0.39

...

-0.39

ch

-0.39

POSITIVE LOGITS

__':

0.95

MLLoader

0.89

 Monfieur

0.87

 itſelf

0.86

цездатний

0.82

 متعلقه

0.80

__":

0.80

 EconPapers

0.79

تقاوى

0.77

MessageTagHelper

0.76

Activations Density 1.196%

scientific terms related to numerical data analysis and properties

No Comments

No Known Activations