INDEX

Explanations

specific medical terms and names related to drugs and treatments

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

 surla

-1.03

Външни

-0.73

fromnode

-0.71

hri

-0.69

hio

-0.68

MLLoader

-0.68

 estekak

-0.67

曖昧さ回避

-0.67

 calendriers

-0.67

 Paglinawan

-0.66

POSITIVE LOGITS

ss

0.47

hes

0.45

ikas

0.44

pas

0.44

as

0.44

ssss

0.42

avas

0.42

tik

0.42

das

0.41

Activations Density 0.155%

specific medical terms and names related to drugs and treatments

No Comments

No Known Activations