INDEX

Explanations

terms related to data analysis and collaboration among researchers

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

online learning and computing

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

 Scaling

-0.36

 joka

-0.35

 없습니다

-0.35

 sửa

-0.35

 pulpit

-0.34

럭

-0.34

Publicado

-0.34

forName

-0.33

 vergessen

-0.32

법

-0.32

POSITIVE LOGITS

 Privacidade

0.56

 MaterialApp

0.52

RTEE

0.47

 TextInputType

0.47

peza

0.47

 collecti

0.47

 argint

0.46

 textual

0.44

 Biôgrafia

0.44

BorderFactory

0.43

Activations Density 0.030%

terms related to data analysis and collaboration among researchers

online learning and computing

No Comments

No Known Activations