INDEX

Explanations

terms related to statistical analysis and data evaluation methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

SourceChecksum

-0.59

XmlAccessorType

-0.53

Diweddarwch

-0.51

 NSCoder

-0.51

########.

-0.50

 totalSupply

-0.49

nologue

-0.48

Vidite

-0.48

VIAF

-0.47

 apartments

-0.47

POSITIVE LOGITS

jsxFileName

0.66

ApiOperation

0.65

 StringTokenizer

0.65

LabelTagHelper

0.63

mapStateToProps

0.58

 <<<<<<<<<<<<<<

0.57

 Pingback

0.57

 مشين

0.56

BuildContext

0.56

NameValuePair

0.56

Activations Density 0.421%

terms related to statistical analysis and data evaluation methods

No Comments

No Known Activations