INDEX

Explanations

a mix of elements related to articles, dates, and locations

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

Word after preposition/conjunction

np_acts-logits-general · gemini-2.0-flash

following capitalized word

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 }}"></

-0.71

}{*}{

-0.68

uttavia

-0.66

 entanto

-0.64

 अलावा

-0.63

-};

-0.63

PreferredItem

-0.60

 الأخرى

-0.60

 other

-0.60

Ayrıca

-0.60

POSITIVE LOGITS

 Seorang

0.71

After

0.71

 After

0.71

Amid

0.69

 Sebuah

0.68

Two

0.68

 Amid

0.68

WASHINGTON

0.67

Following

0.67

随着

0.66

Activations Density 0.189%

a mix of elements related to articles, dates, and locations

Word after preposition/conjunction

following capitalized word

No Comments

No Known Activations