INDEX

Explanations

references to projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 uſed

-0.74

paravant

-0.74

 Constitucional

-0.73

 sonriente

-0.72

 récon

-0.71

 constitucional

-0.71

 déchir

-0.70

 Theſe

-0.69

 temprana

-0.66

 réunis

-0.66

POSITIVE LOGITS

 project

2.54

 projects

2.49

 Project

2.33

 Projects

2.19

 PROJECT

2.19

Project

2.18

project

2.17

PROJECT

2.06

Projects

2.02

projects

2.00

Activations Density 0.046%

references to projects

No Comments

No Known Activations