INDEX

Explanations

quantities related to measurements and containers in scientific contexts

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

different types of containers

np_acts-logits-general · gemini-2.0-flash

containers and vessels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

存于互联网档案馆

-0.70

原始内容存档于

-0.67

 bridges

-0.60

bridges

-0.59

 ostavi

-0.57

 Brücke

-0.55

NSIndexPath

-0.54

 Wydawnictwo

-0.53

发表于

-0.52

fromCharCode

-0.52

POSITIVE LOGITS

 container

1.40

 containers

1.23

container

1.20

 Container

1.12

 bowl

1.12

jar

1.04

容器

1.04

 bucket

1.03

 tank

1.02

Container

1.02

Activations Density 0.380%

quantities related to measurements and containers in scientific contexts

different types of containers

containers and vessels

No Comments

No Known Activations