INDEX

Explanations

terms related to medical conditions and treatment processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

MLLoader

-0.40

 térmico

-0.40

 lavadora

-0.40

 laboratoire

-0.38

脸上

-0.38

sizeCache

-0.37

 medalla

-0.36

 Pernambuco

-0.34

 libremente

-0.34

 conciencia

-0.34

POSITIVE LOGITS

DockStyle

0.56

 bezeichneter

0.56

UserScript

0.54

oredCriteria

0.53

 Normdatei

0.52

RTEE

0.52

 betweenstory

0.52

XmlEnum

0.52

Diweddarwch

0.50

Activations Density 0.853%

terms related to medical conditions and treatment processes

No Comments

No Known Activations