INDEX

Explanations

terms related to databases and software architecture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 cebolla

-0.48

 Trello

-0.48

postValue

-0.47

 Xbox

-0.44

 Dropbox

-0.44

DJI

-0.44

污

-0.43

 Baltic

-0.43

thâu

-0.43

 Asus

-0.43

POSITIVE LOGITS

 Oracle

0.68

EndGlobalSection

0.65

DockStyle

0.64

 oracle

0.63

Oracle

0.62

ativement

0.62

esModule

0.62

 كومونز

0.61

XE

0.60

 cathédrale

0.59

Activations Density 0.346%

terms related to databases and software architecture

No Comments

No Known Activations