INDEX

Explanations

technical terms and references related to programming and project management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

PerformLayout

-0.53

 مُعرِّف

-0.47

GRANTED

-0.46

 désactiv

-0.45

MessageTagHelper

-0.45

ialis

-0.45

eneuve

-0.45

 sortes

-0.44

 alat

-0.44

 getchar

-0.44

POSITIVE LOGITS

SceneManagement

0.90

DataSnapshot

0.78

 AppModule

0.72

 initComponents

0.69

 parishes

0.69

RunWith

0.67

 createSlice

0.67

 configureStore

0.66

<?

0.65

sucurs

0.64

Activations Density 1.240%

technical terms and references related to programming and project management

No Comments

No Known Activations