INDEX

Explanations

temporal and numerical references related to study durations and intervals

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

Numbers (often) followed by units of time

np_acts-logits-general · gemini-2.0-flash

time periods or durations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

RenderAtEndOf

-0.70

 referenties

-0.62

ieteur

-0.58

IGraphics

-0.57

Geplaatst

-0.56

AnchorTagHelper

-0.54

Mutagenicity

-0.54

 busy

-0.53

 waited

-0.53

новништво

-0.53

POSITIVE LOGITS

ValueStyle

0.85

Xna

0.63

 hinweg

0.62

 hinein

0.61

省市镇

0.60

 boyunca

0.59

 aikana

0.59

gående

0.59

فایل‌لار

0.58

 giudi

0.57

Activations Density 0.997%

temporal and numerical references related to study durations and intervals

Numbers (often) followed by units of time

time periods or durations

No Comments

No Known Activations