INDEX

Explanations

references to authorship and acknowledgement in research contexts

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

author, applicant, candidate

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

aarrggbb

-0.57

Rüyada

-0.54

yntaxException

-0.49

 SwiftUI

-0.48

⤹

-0.48

 linkovi

-0.47

preduce

-0.46

 playmobil

-0.44

MutableLiveData

-0.43

ⓘ

-0.43

POSITIVE LOGITS

webElementXpaths

0.54

ViewImports

0.40

gradu

0.35

 Completed

0.35

 Geraadpleegd

0.35

 NgModule

0.34

yonel

0.34

Odkazy

0.33

completed

0.33

 completed

0.33

Activations Density 0.009%

references to authorship and acknowledgement in research contexts

author, applicant, candidate

No Comments

No Known Activations