INDEX

Explanations

programming or technical terminology related to software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

paramMap

-0.51

 tajam

-0.48

lovakia

-0.46

TestingModule

-0.45

himovic

-0.45

initComponents

-0.45

зацию

-0.44

 StatefulWidget

-0.44

зация

-0.43

toggler

-0.43

POSITIVE LOGITS

 ویکی‌پدیای

0.66

^(@)

0.64

клопе

0.62

stdafx

0.61

väg

0.60

thenReturn

0.59

TemporalType

0.59

 calendriers

0.58

erapeu

0.58

BeforeClass

0.53

Activations Density 0.044%

programming or technical terminology related to software development

No Comments

No Known Activations