INDEX

Explanations

terms related to reduction or minimizing something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DockStyle

-0.82

mazoo

-0.78

WebServlet

-0.74

 ujednoznacz

-0.73

 المعيارى

-0.70

 AssemblyCompany

-0.68

onavir

-0.67

нгредіє

-0.67

 Wikispecies

-0.67

versy

-0.66

POSITIVE LOGITS

 reduction

1.82

 Reduce

1.81

 reduce

1.79

Reduce

1.77

 reduc

1.76

reduce

1.73

 reduced

1.72

 reducing

1.72

 Reduction

1.66

 Reduced

1.66

Activations Density 0.067%

terms related to reduction or minimizing something

No Comments

No Known Activations