INDEX

Explanations

phrases that discuss health benefits and wellness interventions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

المكان

-0.51

참고

-0.49

hebt

-0.49

Begriffsklä

-0.48

 disgusted

-0.48

 jspb

-0.48

 ControllerBase

-0.48

 AppCompatTheme

-0.47

appara

-0.47

espo

-0.47

POSITIVE LOGITS

 benefits

2.99

 Benefits

2.52

benefits

2.50

 benefit

2.43

Benefits

2.41

 BENEFITS

2.31

benefit

2.16

Benefit

2.14

BENEFITS

2.12

 Benefit

2.05

Activations Density 0.451%

phrases that discuss health benefits and wellness interventions

No Comments

No Known Activations