INDEX

Explanations

chemical compounds and medical terminology related to health and treatments.

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

medical and laboratory terminologies related to treatments and applications.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

words or abbreviations related to medical or scientific terms, particularly those starting with "ST" or containing "ent".

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

Tokens "ST" or "st" followed by other letters

np_acts-logits-general · gemini-2.0-flash

st abbreviations and technical terms

np_acts-logits-general · gemini-2.5-flash-lite

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

__':

-0.89

__":

-0.73

انجليز

-0.69

tanleria

-0.68

WindowConstants

-0.66

orianCalendar

-0.66

__":

-0.64

 strict

-0.63

 Theological

-0.62

])):

-0.61

POSITIVE LOGITS

quo

0.61

Hilfe

0.58

MigrationBuilder

0.57

 fotográfico

0.53

STP

0.52

 AppComponent

0.52

getWriter

0.51

multer

0.51

ButterKnife

0.50

trooper

0.49

Activations Density 0.631%