INDEX

Explanations

medical terms related to health outcomes and statistics

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

providedIn

-0.61

 rhestr

-0.56

 Tempest

-0.54

तान

-0.54

 uska

-0.54

pagestyle

-0.52

 students

-0.48

ellen

-0.48

ocu

-0.47

onViewCreated

-0.46

POSITIVE LOGITS

WithIOException

0.72

-------------</

0.63

SharedCtor

0.63

AndEndTag

0.63

LookAnd

0.63

Viited

0.61

 avoient

0.61

clerview

0.60

newBuilder

0.59

Vidite

0.57

Activations Density 0.636%

medical terms related to health outcomes and statistics

No Comments

No Known Activations