INDEX

Explanations

references to specific plans or frameworks, often labeled as 'schemes'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

EAT

-0.82

 Constan

-0.74

 Garry

-0.71

 Horton

-0.69

mort

-0.69

Ata

-0.68

Visual

-0.67

tq

-0.66

 Visual

-0.65

 faſt

-0.64

POSITIVE LOGITS

 scheme

2.54

scheme

2.50

 Scheme

2.48

 SCHEME

2.48

 Schemes

2.46

 schemes

2.44

Scheme

2.39

schemes

2.27

Schemes

2.22

SCHEME

2.07

Activations Density 0.103%

references to specific plans or frameworks, often labeled as 'schemes'

No Comments

No Known Activations