INDEX

Explanations

references to independence in 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 @ 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

OGND

-0.82

 Roskov

-0.81

ContentAlignment

-0.72

expandindo

-0.68

dagog

-0.65

примеча

-0.63

❦

-0.63

WHEREAS

-0.63

reactor

-0.63

 RequestMethod

-0.62

POSITIVE LOGITS

 independent

3.57

 Independent

3.43

Independent

3.35

independent

3.23

 INDEPENDENT

2.98

 independ

2.77

 independently

2.65

 independence

2.60

 Independ

2.57

 Indep

2.56

Activations Density 0.073%

references to independence in various contexts

No Comments

No Known Activations