INDEX

Explanations

specialized vocabulary and terminology used in various contexts

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

Vocabulary, jargon, and terminology

np_acts-logits-general · gemini-2.0-flash

terms, terminology, glossary, vocabulary

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

setVerticalGroup

-0.40

ClientSize

-0.33

ьаж

-0.33

RunWith

-0.33

OCCURRED

-0.32

vdots

-0.32

 nahilalakip

-0.31

borderFill

-0.31

Nationalité

-0.31

 Meksiku

-0.30

POSITIVE LOGITS

 term

0.98

 terminology

0.95

 glossary

0.95

 Terminology

0.95

 Glossary

0.94

 vocabulary

0.91

Glossary

0.90

OSSARY

0.88

 terms

0.87

 Term

0.87

Activations Density 0.498%

specialized vocabulary and terminology used in various contexts

Vocabulary, jargon, and terminology

terms, terminology, glossary, vocabulary

No Comments

No Known Activations