INDEX

Explanations

technical terms and topics related to file formats, compatibility, and data handling in programming and software contexts

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

support, characters, reduce, permit

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

 Jefus

-0.56

Efq

-0.50

GOTREF

-0.50

DockStyle

-0.49

 للمعارف

-0.48

 pleaſure

-0.48

 سكانية

-0.47

 COMPETITION

-0.46

Competition

-0.46

enterOuterAlt

-0.46

POSITIVE LOGITS

 universal

0.44

wr

0.42

Universal

0.41

 Universal

0.39

universal

0.38

quila

0.38

الحياه

0.37

vet

0.36

Py

0.36

 pior

0.35

Activations Density 0.164%

technical terms and topics related to file formats, compatibility, and data handling in programming and software contexts

support, characters, reduce, permit

No Comments

No Known Activations