INDEX

Explanations

terms related to trials and medical evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Meksiku

-0.81

 nahilalakip

-0.79

 Савезне

-0.69

enumi

-0.68

 Exacts

-0.65

 ErrIntOverflow

-0.63

 MainAxisSize

-0.63

 MenuView

-0.63

MessageState

-0.63

gants

-0.62

POSITIVE LOGITS

0.82

</strong>

0.65

 تانيه

0.63

 للمعارف

0.63

Tembelea

0.57

xase

0.55

mässig

0.55

Архівовано

0.55

 piú

0.53

</em>

0.53

Activations Density 3.597%

terms related to trials and medical evaluations

No Comments

No Known Activations