INDEX

Explanations

phrases related to quantitative comparisons or levels of measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

يكب

-0.74

AndEndTag

-0.73

rateful

-0.66

AutoScaleMode

-0.66

 jScrollPane

-0.65

 kasarigan

-0.64

 GreatSchools

-0.64

lapsingToolbar

-0.63

})));

-0.63

tanleria

-0.63

POSITIVE LOGITS

 than

1.88

than

1.28

 THAN

1.27

Than

1.14

 niż

1.06

 Than

1.06

 hơn

1.05

THAN

0.97

 harder

0.92

 kuin

0.88

Activations Density 0.494%

phrases related to quantitative comparisons or levels of measurement

No Comments

No Known Activations