INDEX

Explanations

technical terms and concepts related to systems and components in various fields

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

power supply

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

windowFixed

-0.58

Réalisation

-0.56

новниш

-0.51

InvalidProtocol

-0.50

エース

-0.50

 Prophe

-0.46

Champion

-0.46

RTCK

-0.45

sizeCache

-0.45

RegistryLite

-0.44

POSITIVE LOGITS

transQ

0.53



0.39

muerzo

0.39

 المعيارى

0.39

WithIOException

0.37

SBATCH

0.35

ėmis

0.35

 saurait

0.34

گاب

0.34

 indirec

0.33

Activations Density 0.105%

technical terms and concepts related to systems and components in various fields

power supply

No Comments

No Known Activations