INDEX

Explanations

references to educational institutions, specifically colleges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

SourceChecksum

-0.83

 piatta

-0.78

DispatchToProps

-0.77

 Réponses

-0.77

UpInside

-0.76

SuppressMessage

-0.76

adaptiveStyles

-0.76

msgSender

-0.75

grafie

-0.74

 parishi

-0.74

POSITIVE LOGITS

 college

3.04

 College

2.98

College

2.73

college

2.69

 COLLEGE

2.65

 colleges

2.48

COLLEGE

2.32

 Colleges

2.19

 collegiate

1.50

 Colleg

1.49

Activations Density 0.028%

references to educational institutions, specifically colleges

No Comments

No Known Activations