INDEX

Explanations

phrases related to limitations in capability or coverage

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

Preceding tokens of "all"

np_acts-logits-general · gemini-2.0-flash

all or everything

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 disambiguazione

-0.70

Portale

-0.64

 دیکھیے

-0.55

 surla

-0.54

 tartalomajánló

-0.54

 Sometimes

-0.52

PropertyChanging

-0.52

➟

-0.52

IntoConstraints

-0.50

RSpec

-0.49

POSITIVE LOGITS

all

2.94

 everything

2.56

 semua

2.42

everything

2.42

 todas

2.41

 tutte

2.40

 всех

2.32

 EVERYTHING

2.23

 every

2.23

 todos

2.19

Activations Density 2.434%

phrases related to limitations in capability or coverage

Preceding tokens of "all"

all or everything

No Comments

No Known Activations