INDEX

Explanations

references to projects or initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 écl

-0.72

paravant

-0.71

 uſed

-0.71

 Cuff

-0.69

antlr

-0.69

 Constitucional

-0.69

 Theſe

-0.68

 Laat

-0.68

 Checker

-0.65

 sonriente

-0.64

POSITIVE LOGITS

 projects

1.71

 project

1.61

 Projects

1.52

 Project

1.51

 PROJECT

1.48

PROJECT

1.40

Project

1.39

project

1.38

Projects

1.36

projects

1.32

Activations Density 0.045%

references to projects or initiatives

No Comments

No Known Activations