INDEX

Explanations

terms related to design and designers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

RUPT

-0.55

tal

-0.53

Vor

-0.52

«

-0.50

dawnictwo

-0.50

 الف

-0.48

fan

-0.48

нг

-0.47

 Tale

-0.47

Plots

-0.46

POSITIVE LOGITS

 designing

1.57

 Designing

1.48

Designing

1.34

design

1.24

 diseño

1.18

 Designers

1.15

 DESIGN

1.14

DESIGN

1.14

 Designer

1.13

 designed

1.13

Activations Density 0.192%

terms related to design and designers

No Comments

No Known Activations