INDEX

Explanations

details about authorship and literary works

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

Publications or creations

np_acts-logits-general · gemini-2.0-flash

quantified creative works

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Мексичка

-0.51

aarrggbb

-0.49

 ExecuteAsync

-0.48

sidemargin

-0.48

GTCX

-0.47

Chham

-0.47

 <<<<<<<<<<<<<<

-0.47

 fevere

-0.46

 estekak

-0.45

 <=",

-0.44

POSITIVE LOGITS

 published

0.58

 creations

0.56

 productions

0.56

 albums

0.52

 publications

0.52

 titles

0.50

 novels

0.50

productions

0.48

published

0.48

bibliography

0.48

Activations Density 0.209%

details about authorship and literary works

Publications or creations

quantified creative works

No Comments

No Known Activations