INDEX

Explanations

terms and concepts related to standards and quality in various contexts

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

Good [X] (concept, movie, developers, book, app, strategy, ideas)

np_acts-logits-general · gemini-2.0-flash

good [entity] is

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 préféré

-0.71

évaluateur

-0.71

fastjson

-0.63

 préf

-0.61

odat

-0.61

 préférence

-0.58

 direta

-0.52

ResponseWriter

-0.52

 dieux

-0.51

DrawerToggle

-0.51

POSITIVE LOGITS

 فريبيس

0.59

Hentet

0.58

 насељу

0.57

 AssemblyCompany

0.57

 ddelweddau

0.55

 Roskov

0.55

 Bioaccumulative

0.54

 estekak

0.53

 BoxDecoration

0.53

Спасылкі

0.53

Activations Density 0.390%

terms and concepts related to standards and quality in various contexts

Good [X] (concept, movie, developers, book, app, strategy, ideas)

good [entity] is

No Comments

No Known Activations