INDEX

Explanations

syntax related to formal writing or complex structures

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

academic citations and procedures

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

 defaultstate

-0.48

 Tasche

-0.42

 Reif

-0.41

voer

-0.41

SequentialGroup

-0.41

ⓧ

-0.40

 Schäfer

-0.39

 paraître

-0.39

 katkı

-0.39

 Beiträge

-0.38

POSITIVE LOGITS

:✨

0.88

 Италијани

0.73

Personensuche

0.63

GEBURTSDATUM

0.60

 المعيارى

0.59

➯

0.54

wargs

0.53

}-*/;

0.52

 kasarigan

0.51

UnusedPrivate

0.50

Activations Density 0.001%

syntax related to formal writing or complex structures

academic citations and procedures

No Comments

No Known Activations