INDEX

Explanations

technical terms and references related to software, particularly those involving commands and configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 elettrica

-0.82

 veneta

-0.80

 frescas

-0.80

 navideña

-0.79

 asiática

-0.78

 humaines

-0.77

 suprême

-0.76

 italienne

-0.75

 muerta

-0.74

 popolare

-0.73

POSITIVE LOGITS

de

0.70

0.64

balleur

0.60

Abitanti

0.59

AutoField

0.56

=").

0.54

 متعلقه

0.54

ódz

0.53

zzleHttp

0.53

himself

0.53

Activations Density 0.123%

technical terms and references related to software, particularly those involving commands and configurations

No Comments

No Known Activations