INDEX

Explanations

terms that reference statistical distributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

enterOuterAlt

-0.84

 nahilalakip

-0.80

oredCriteria

-0.77

 Theſe

-0.75

webElementXpaths

-0.71

Gambas

-0.70

Jeografia

-0.65

 فريبيس

-0.65

发表于

-0.64

]")]

-0.63

POSITIVE LOGITS

 distribution

1.13

distribution

0.91

 Distribution

0.86

Distribution

0.86

 DISTRIBUTION

0.69

 distributions

0.66

Distribución

0.66

 distribuição

0.65

 Verteilung

0.63

 distribución

0.61

Activations Density 0.174%

terms that reference statistical distributions

No Comments

No Known Activations