INDEX

Explanations

medical-related terminology, particularly surrounding diseases and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

zate

-0.59

 Meksiku

-0.59

 bald

-0.56

 ulang

-0.53

SplashScreen

-0.52

 mosques

-0.50

alda

-0.50

opley

-0.49

 proceed

-0.49

 rods

-0.49

POSITIVE LOGITS

bing

0.85

Tikang

0.78

bed

0.72

sinon

0.72

 vPvB

0.70

 MainAxisSize

0.70

bs

0.68

OrBuilder

0.67

SCRIBE

0.62

setVerticalGroup

0.62

Activations Density 0.700%

medical-related terminology, particularly surrounding diseases and conditions

No Comments

No Known Activations