INDEX

Explanations

acknowledgments of individuals' contributions to research or projects

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

proper names and titles

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

 pinulongan

-0.69

LookAnd

-0.58

tagHelperRunner

-0.56

 ब्रेकडाउन

-0.48

transQ

-0.46

 kaarangay

-0.46

 للمعارف

-0.45

 cherchés

-0.45

ientras

-0.44

ppuden

-0.44

POSITIVE LOGITS

 brothers

0.46

of

0.45

 banish

0.44

 Cardoso

0.44

 Blank

0.44

 renegade

0.43

呼ぶ

0.43

 Brother

0.43

Brothers

0.43

Activations Density 0.020%

acknowledgments of individuals' contributions to research or projects

proper names and titles

No Comments

No Known Activations