INDEX

Explanations

keywords related to virtual environments and experiences

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

Vidite

-0.81

 OkHttpClient

-0.78

 élector

-0.76

 canzoni

-0.74

PYX

-0.73

createStatement

-0.72

 testigo

-0.69

 guste

-0.69

lewood

-0.67

 policia

-0.67

POSITIVE LOGITS

 virtual

2.27

 Virtual

2.13

Virtual

2.12

virtual

2.09

 VIRTUAL

2.07

VIRTUAL

1.94

 virtuelle

1.72

虚拟

1.52

 virtuel

1.51

 virtuales

1.49

Activations Density 0.048%

keywords related to virtual environments and experiences

No Comments

No Known Activations