INDEX

Explanations

nothing, as it does not activate for any content

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

Code snippets or markup

np_acts-logits-general · gemini-2.0-flash

surcharge offer

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 سكانية

-0.67

 فريبيس

-0.66

 invokingState

-0.64

LookAnd

-0.60

{{/

-0.60

 Wicidata

-0.58

 lenker

-0.57

XtraReports

-0.56

 виправивши

-0.55

']>

-0.55

POSITIVE LOGITS

PointerException

0.64

 varandra

0.61

ArgsConstructor

0.61

 springfox

0.54

schung

0.53

 ioutil

0.51

 stället

0.51

melho

0.50

 AUSTRALIA

0.48

orcid

0.48

Activations Density 0.032%

nothing, as it does not activate for any content

Code snippets or markup

surcharge offer

No Comments

No Known Activations