INDEX

Explanations

keywords related to memory and addressing in computer architecture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ValueStyle

-0.85

 arşivlendi

-0.81

webElementXpaths

-0.78

 Normdatei

-0.76

twimg

-0.76

 nahilalakip

-0.68

 gepubliceerd

-0.67

 Superhosts

-0.66

iastes

-0.66

сылкі

-0.63

POSITIVE LOGITS

mem

1.67

Mem

1.57

mem

1.56

Mem

1.47

Memory

1.41

 Memory

1.41

 memory

1.38

memory

1.36

MEMORY

1.28

 MEMORY

1.25

Activations Density 0.094%

keywords related to memory and addressing in computer architecture

No Comments

No Known Activations