INDEX

Explanations

repeated phrases or structures with a numerical emphasis, possibly indicating patterns or sequences

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

The digit 1

np_acts-logits-general · gemini-2.0-flash

years and dates

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

 WaitForSeconds

-1.14

AccessorTable

-1.13

 ویکی‌پدیای

-1.01

 AssemblyVersion

-1.00

GraphicsUnit

-0.98

WaitGroup

-0.95

Портали

-0.94

GEBURTSDATUM

-0.94

matchCondition

-0.93

oneofs

-0.92

POSITIVE LOGITS

0.73

0.65

0.64

0.63

0.60

0.59

0.58

Activations Density 0.115%

repeated phrases or structures with a numerical emphasis, possibly indicating patterns or sequences

The digit 1

years and dates

No Comments

No Known Activations