INDEX

Explanations

terms related to memory systems and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 виправивши

-0.83

ScopeManager

-0.78

]")]

-0.76

AndEndTag

-0.74

IntoConstraints

-0.70

はじめに

-0.63

msgTypes

-0.63

MemoryWarning

-0.62

ValueStyle

-0.62

+#+

-0.61

POSITIVE LOGITS

ofollow

0.39

ÕES

0.35

nocześnie

0.34

MLLoader

0.34

правления

0.34

 kautta

0.34

žený

0.34

wakeup

0.34

Fermi

0.34

Autriche

0.33

Activations Density 0.987%

terms related to memory systems and their components

No Comments

No Known Activations