INDEX

Explanations

technical terms and abbreviations related to computer programming and data structures

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

Tokens after particular names or abbreviations

np_acts-logits-general · gemini-2.0-flash

SOP ORGANIZATION PAC PL VIEWS

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

aski

-0.41

 Polsek

-0.41

gger

-0.40

談

-0.38

 vinto

-0.38

pl

-0.37

pry

-0.37

軋

-0.36

плек

-0.36

ubel

-0.36

POSITIVE LOGITS

MemoryWarning

0.91

+#+#

0.84

EndProject

0.83

webElementGuid

0.80

Efq

0.78

ButterKnife

0.77

 تضيفلها

0.77

 EconPapers

0.77

IntoConstraints

0.77

 nakalista

0.76

Activations Density 0.319%

technical terms and abbreviations related to computer programming and data structures

Tokens after particular names or abbreviations

SOP ORGANIZATION PAC PL VIEWS

No Comments

No Known Activations