INDEX

Explanations

phrases that denote inclusion or reference to additional elements or conditions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 houſe

-0.87

 purpoſe

-0.79

 humaines

-0.78

 ſche

-0.73

 ftate

-0.73

 ſtate

-0.71

 getItemId

-0.70

 sandero

-0.70

 Philo

-0.67

 cauſe

-0.66

POSITIVE LOGITS

 including

1.28

INCLUDING

1.16

 Including

1.13

including

1.12

Including

1.10

 INCLUDING

1.06

 includes

0.99

 waaronder

0.96

 einschließlich

0.96

 включая

0.95

Activations Density 0.111%

phrases that denote inclusion or reference to additional elements or conditions

No Comments

No Known Activations