INDEX

Explanations

references to independence and independent entities across various contexts

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

ioutil

-0.81

 JTextArea

-0.75

dagog

-0.72

μως

-0.72

ContentAlignment

-0.72

WHEREAS

-0.70

 Roskov

-0.68

HRM

-0.68

 setShow

-0.67

jillo

-0.67

POSITIVE LOGITS

 independent

2.54

 Independent

2.47

Independent

2.43

independent

2.32

 INDEPENDENT

2.21

 independence

2.15

 independ

2.10

 independently

1.98

 Independ

1.95

 Indep

1.95

Activations Density 0.088%

references to independence and independent entities across various contexts

No Comments

No Known Activations