INDEX

Explanations

references to core components in a software framework

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

 ICollection

-0.54

发表于

-0.51

ArrowToggle

-0.50

DrawerToggle

-0.48

Jam

-0.44

assage

-0.44

Nielsen

-0.43

 borderRadius

-0.42

ObservableList

-0.42

 gelo

-0.41

POSITIVE LOGITS

core

2.38

CORE

1.60

Core

1.59

 core

1.29

 Core

1.22

cores

1.18

 CORE

1.17

rrggbb

1.05

cored

0.99

コア

0.93

Activations Density 0.029%

references to core components in a software framework

No Comments

No Known Activations