INDEX

Explanations

references to design processes and related terminology

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

WebVitals

-1.15

 pitié

-0.92

 snippetHide

-0.85

fycat

-0.84

 Hotspur

-0.81

GEBURTSDATUM

-0.80

̍t

-0.78

 épar

-0.78

 Geophysics

-0.78

FontAwesomeIcon

-0.78

POSITIVE LOGITS

 design

1.48

 designs

1.42

 Design

1.37

Design

1.30

 Designs

1.26

designs

1.15

 designers

1.15

Designs

1.14

design

1.13

DESIGN

1.10

Activations Density 0.041%

references to design processes and related terminology

No Comments

No Known Activations