INDEX

Explanations

questions about how to perform tasks or solve problems

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

"How can I" questions

np_acts-logits-general · gemini-2.0-flash

how can I ask

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

تقاوى

-0.98

SharedCtor

-0.87

 doInBackground

-0.87

 Roskov

-0.86

Portale

-0.81

oredCriteria

-0.81

èdia

-0.78

يكب

-0.76



-0.75

 <<<<<<<<<<<<<<

-0.74

POSITIVE LOGITS

we

1.27

you

1.22

 você

0.72

เรา

0.68

我们

0.67

 мы

0.67

we

0.65

you

0.64

我們

0.64

我把

0.60

Activations Density 0.443%

questions about how to perform tasks or solve problems

"How can I" questions

how can I ask

No Comments

No Known Activations