INDEX

Explanations

negative findings or denials of associations in research contexts

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

after punctuation, especially commas and periods

np_acts-logits-general · gemini-2.0-flash

nonreactive or did not

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

GGLE

-0.49

gam

-0.47

RTHOOK

-0.45

 attra

-0.41

SupportActionBar

-0.39

Grad

-0.39

RRect

-0.39

 retrieve

-0.38

 programme

-0.38

 فريبيس

-0.38

POSITIVE LOGITS

eningrad

0.51

 consciência

0.51

 ReactDOM

0.49

 giudi

0.44

verwijspagina

0.44

 onCreateView

0.43

 conclusão

0.43

 infância

0.42

powied

0.42

ostante

0.42

Activations Density 1.337%

negative findings or denials of associations in research contexts

after punctuation, especially commas and periods

nonreactive or did not

No Comments

No Known Activations