INDEX

Explanations

references to concepts related to "multiple" or "multi-" in a variety of contexts

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

Followed by specific medical conditions or statistical analysis

np_acts-logits-general · gemini-2.0-flash

Multiple statistical or medical 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCompany

-0.89

#+#

-0.65

 /*#__

-0.63

stalt

-0.60

:✨

-0.59

цездатний

-0.58

 modifié

-0.58

 jScrollPane

-0.58

 initComponents

-0.57

 LoggerFactory

-0.57

POSITIVE LOGITS

 myeloma

1.26

 sclerosis

1.17

xer

1.00

xed

0.98

xing

0.96

xes

0.84

eloma

0.83

 malen

0.82

clerosis

0.69

IEU

0.66

Activations Density 0.128%

references to concepts related to "multiple" or "multi-" in a variety of contexts

Followed by specific medical conditions or statistical analysis

Multiple statistical or medical terms

No Comments

No Known Activations