INDEX

Explanations

instances of user engagement or interaction

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

don't

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

IntoConstraints

-0.57

Personendaten

-0.49

Архівовано

-0.47

 كومونز

-0.46

 ModelExpression

-0.44

不堪

-0.42

InstanceState

-0.41

NamedQueries

-0.40

fortawesome

-0.40

 grieved

-0.40

POSITIVE LOGITS

хьтан

0.54

 Italijanski

0.47

:✨

0.46

 Numerade

0.45

bcryptjs

0.43

'{@

0.42

Бележки

0.42

 Profesional

0.42

featureID

0.41

COW

0.41

Activations Density 0.195%

instances of user engagement or interaction

don't

No Comments

No Known Activations