INDEX

Explanations

concepts related to healthcare and medical interventions

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

 ſmall

-0.61

 LoginForm

-0.60

 Leech

-0.56

EPO

-0.56

xically

-0.55

 ſeveral

-0.54

 mero

-0.53

 figures

-0.53

OCR

-0.53

 drafts

-0.52

POSITIVE LOGITS

脚注の使い方

0.57

SharedDtor

0.56

 pensées

0.51

 œufs

0.50

 descrizione

0.50

 específicos

0.50

 objectifs

0.50

iastes

0.49

 rayures

0.49

 action

0.49

Activations Density 0.484%

concepts related to healthcare and medical interventions

No Comments

No Known Activations