INDEX

Explanations

references to recent studies and advancements

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

Follows "recent" referring to time

np_acts-logits-general · gemini-2.0-flash

recent years, studies, work, advances

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

 soon

-0.73

 tomorrow

-0.71

 currently

-0.70

 eventually

-0.69

 uiteindelijk

-0.66

eventually

-0.66

 actuellement

-0.65

currently

-0.63

 بيها

-0.63

 presently

-0.62

POSITIVE LOGITS

 resourceCulture

0.93

PerformLayout

0.89

MemoryWarning

0.83

 spate

0.82

 additions

0.78

 "'");

0.76

بوابة

0.74

windowFixed

0.73

trends

0.73

 trends

0.73

Activations Density 0.091%

references to recent studies and advancements

Follows "recent" referring to time

recent years, studies, work, advances

No Comments

No Known Activations