INDEX

Explanations

mathematical symbols and notation relevant to equations and expressions in topology or algebra

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 NgModule

-0.51

FormTagHelper

-0.50

 paus

-0.48

 savon

-0.48

 ciga

-0.46

toc

-0.46

 gammal

-0.46

 LoggerFactory

-0.45

</sup>

-0.45

kin

-0.45

POSITIVE LOGITS

AndEndTag

0.78

abestanden

0.73

ValueStyle

0.71

WillAppear

0.61

TintMode

0.61

TestingModule

0.58

ropshire

0.54

TagMode

0.54

جوايز

0.52

ItemBackground

0.51

Activations Density 2.111%

mathematical symbols and notation relevant to equations and expressions in topology or algebra

No Comments

No Known Activations