INDEX

Explanations

URLs and web addresses

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

domain names

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

/*---

-0.44

Descripció

-0.43

muerzo

-0.42

Traduction

-0.42

Kris

-0.41

 środków

-0.41

Xna

-0.40

SharedCtor

-0.39

omitempty

-0.39

 Kris

-0.39

POSITIVE LOGITS

www

0.53

www

0.47

://"

0.46

://$

0.45

 NSCoder

0.44

 website

0.44

Notae

0.43

AutoField

0.42

⟭

0.41

htu

0.41

Activations Density 0.076%

URLs and web addresses

domain names

No Comments

No Known Activations

URLs and web addresses

domain names

No Comments

No Known Activations