INDEX

Explanations

mathematical equations and symbols used in formulations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</blockquote>

-0.41

ссор

-0.41

lanması

-0.40

 them

-0.39

有何

-0.39

ard

-0.39

ροσ

-0.38

 then

-0.38

らを

-0.37

 meningkat

-0.37

POSITIVE LOGITS

 AssemblyCompany

0.88

DebuggerStep

0.88

 незавершена

0.85

 CreateTagHelper

0.83

rungsseite

0.83

DotNetBar

0.79

 للمعارف

0.77

EDEFAULT

0.74

'{@

0.74

WriteTagHelper

0.73

Activations Density 0.563%

mathematical equations and symbols used in formulations

No Comments

No Known Activations