INDEX

Explanations

numbers and sequences typical in data or programming contexts

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

Times and dates with timezone offsets

np_acts-logits-general · gemini-2.0-flash

timestamps followed by +

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

 lenker

-0.56

aragus

-0.56

ISupport

-0.56

AndroidJUnit

-0.55

 saites

-0.54

lijks

-0.51

 HasFactory

-0.51

🏾

-0.51

 []).

-0.51

".

-0.50

POSITIVE LOGITS

BeginContext

0.74

 StatefulWidget

0.71

tvguidetime

0.66

posedge

0.64

 StatelessWidget

0.63

帖最后由

0.59

ViewInit

0.58

 devriez

0.57

ظام

0.56

 виправивши

0.56

Activations Density 0.232%

numbers and sequences typical in data or programming contexts

Times and dates with timezone offsets

timestamps followed by +

No Comments

No Known Activations