INDEX

Explanations

accurate descriptions of successful medical procedures and patient 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

{?

-0.49

жели

-0.45

resave

-0.43

 certain

-0.43

SME

-0.42

?</

-0.42

mée

-0.41

certain

-0.41

 Berber

-0.40

NewUrlParser

-0.40

POSITIVE LOGITS

 intact

0.80

 smooth

0.73

 smoothly

0.72

 strå

0.69

 satisfactory

0.69

 flawless

0.67

 utafitiHapana

0.66

 happily

0.65

webElement

0.65

 Sufficient

0.64

Activations Density 0.652%

accurate descriptions of successful medical procedures and patient evaluations

No Comments

No Known Activations