INDEX

Explanations

references to patients and medical cases in research studies

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

ailleurs

-0.55

 مرئيه

-0.47

 Lise

-0.47

maphore

-0.45

ESTER

-0.43

 Therapist

-0.42

 połą

-0.42

Mnemonic

-0.42

ammans

-0.42

 Италијани

-0.42

POSITIVE LOGITS

StoryboardSegue

0.75

copg

0.69

NgModule

0.64

 typelib

0.63

 protoimpl

0.60

 الحره

0.59

 ProtoMessage

0.58

posób

0.57

 EconPapers

0.57

 ModelExpression

0.56

Activations Density 1.272%

references to patients and medical cases in research studies

No Comments

No Known Activations