INDEX

Explanations

terms related to booting processes and startup functions

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

 Réponses

-0.57

 Ives

-0.55

 indisponible

-0.54

 Exactos

-0.53

дивиду

-0.53

chartInstance

-0.52

 الرياضيه

-0.52

 disambiguazione

-0.50

Millan

-0.50

 sufic

-0.48

POSITIVE LOGITS

 boots

0.82

RetentionPolicy

0.79

CloseOperation

0.77

👢

0.77

 Boot

0.76

XmlRootElement

0.75

Boots

0.74

DebuggerNonUser

0.73

 boot

0.73

 Boots

0.71

Activations Density 0.098%

terms related to booting processes and startup functions

No Comments

No Known Activations