INDEX

Explanations

references to organizations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 urbaine

-0.60

Dud

-0.54

Shutterstock

-0.53

 estético

-0.52

Bif

-0.52

вших

-0.52

 larmes

-0.51

彿

-0.51

 térmica

-0.51

klä

-0.50

POSITIVE LOGITS

 organization

3.51

 organisation

3.21

 Organization

3.19

 Organisation

2.90

organization

2.86

Organization

2.85

 ORGANIZATION

2.82

 organizations

2.72

organisation

2.55

 Organizations

2.55

Activations Density 0.085%

references to organizations

No Comments

No Known Activations