INDEX

Explanations

terminologies related to medical coding and references to health parameters

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

-0.59

par

-0.57

...

-0.53

-0.49

-0.48

“

-0.48

-0.47

..

-0.46

POSITIVE LOGITS

+#+#

1.06

rungsseite

1.06

IntoConstraints

0.94

 препратки

0.93

 مرئيه

0.93

verwijspagina

0.92

 للاسماء

0.91

المناصب

0.89

EndInit

0.89

 defaultstate

0.89

Activations Density 0.701%

terminologies related to medical coding and references to health parameters

No Comments

No Known Activations