INDEX

Explanations

numeric values followed by phrases indicating time or events

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

years followed by a number

np_acts-logits-general · gemini-2.0-flash

years and decades

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

InSection

-0.74

ungsbedingungen

-0.71

ImageContext

-0.69

#+#

-0.68

 ModelExpression

-0.67

errHandler

-0.66

InputTagHelper

-0.65

makeConstraints

-0.65

 ویکی‌آمباردا

-0.65

 חיצוניים

-0.64

POSITIVE LOGITS

 decades

0.59

alia

0.55

 millennia

0.51

arian

0.50

ThemeOverlay

0.49

 centuries

0.47

 cajones

0.46

lit

0.46

 built

0.45

 years

0.44

Activations Density 0.091%

numeric values followed by phrases indicating time or events

years followed by a number

years and decades

No Comments

No Known Activations