INDEX

Explanations

phrases related to measurements and quantification

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

íncia

-0.53

scenarios

-0.53

erráneo

-0.51

gså

-0.50

########.

-0.50

 esternos

-0.48

 scenarios

-0.47

Derp

-0.47

展望

-0.47

ParseTree

-0.45

POSITIVE LOGITS

 measure

2.15

 measuring

2.12

 Measure

1.98

measure

1.94

 Measuring

1.92

 measurement

1.92

 mesure

1.91

Measuring

1.89

 measures

1.87

 MEASURE

1.86

Activations Density 0.316%

phrases related to measurements and quantification

No Comments

No Known Activations