INDEX

Explanations

terms and phrases related to medical and health-related concepts

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 NSCoder

-0.70

UrlResolution

-0.67

:✨

-0.65

 المعيارى

-0.65

الحياه

-0.60

AndEndTag

-0.58

 nakalista

-0.57

 ब्रेकडाउन

-0.56

 GetEnumerator

-0.56

 '\\;'

-0.55

POSITIVE LOGITS

 regulators

0.34

 available

0.31

ActivityResult

0.31

horabuena

0.30

cor

0.30

Worldwide

0.30

økt

0.29

 among

0.28

discovery

0.28

cat

0.28

Activations Density 0.052%

terms and phrases related to medical and health-related concepts

No Comments

No Known Activations