INDEX

Explanations

terms related to statistical analysis and modeling in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

flexDirection

-0.55

 surla

-0.53

 TextAlign

-0.53

 continuant

-0.52

QtWidgets

-0.51

 visibles

-0.50

Ikus

-0.50

ActionBar

-0.49

ayat

-0.49

Präsident

-0.48

POSITIVE LOGITS

 scenarios

0.77

Scenario

0.74

 scenario

0.73

 Scenario

0.72

 Scenarios

0.72

 Sensitivity

0.69

 SWAT

0.68

GIS

0.68

 Normdatei

0.67

scenario

0.67

Activations Density 0.451%

terms related to statistical analysis and modeling in research contexts

No Comments

No Known Activations