INDEX

Explanations

technical terms and references related to research or scientific studies

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

Followed by "tron" or relates to "Artron" company

np_acts-logits-general · gemini-2.0-flash

Artron, arthropathy, Enron

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

 ་་

-0.86

 Theſe

-0.83

 itſelf

-0.77

 ―――――

-0.77

BibitemShut

-0.74

 ainfi

-0.73

таратура

-0.71

 ſind

-0.71

 Monfieur

-0.70

 Anſ

-0.70

POSITIVE LOGITS

 potholes

0.70

 covariates

0.66

Sh

0.63

Ra

0.61

Co

0.60

的自

0.59

Sh

0.57

Ra

0.57

Ar

0.57

Activations Density 0.801%

technical terms and references related to research or scientific studies

Followed by "tron" or relates to "Artron" company

Artron, arthropathy, Enron

No Comments

No Known Activations