INDEX

Explanations

notations and indicators of statistical significance in scientific texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 EconPapers

-0.74

Personendaten

-0.68

Morfologia

-0.63

ScopeManager

-0.62

RuleContext

-0.61

 documentaire

-0.61

Diweddarwch

-0.60

 invertebrates

-0.59

 Pristupljeno

-0.59

IUrlHelper

-0.58

POSITIVE LOGITS

InputTagHelper

0.52

tagHelperRunner

0.49

 bold

0.46

 كومونز

0.44

 here

0.44

red

0.44

マーク

0.44

 chì

0.43

Становништво

0.43

 mark

0.43

Activations Density 0.638%

notations and indicators of statistical significance in scientific texts

No Comments

No Known Activations