INDEX

Explanations

references to complex processes and their implications in various contexts

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

preceding a purpose, basis, period, or format

np_acts-logits-general · gemini-2.0-flash

purposes following specific terms

np_acts-logits-general · gemini-2.5-flash-lite

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

Παραπομπές

-0.48

 CONTENTS

-0.47

ApplicationTests

-0.46

ayana

-0.46

gehe

-0.45

 arşivlendi

-0.45

 consultato

-0.45

 تعدى

-0.44

optarg

-0.44

||||

-0.44

POSITIVE LOGITS

OGND

0.82

fjspx

0.79

 AssemblyCulture

0.76

 typelib

0.70

setVerticalGroup

0.69

 AssemblyProduct

0.69

Personendaten

0.69

 незавершена

0.69

DebuggerNonUser

0.69

 Савезне

0.68

Activations Density 1.210%

references to complex processes and their implications in various contexts

preceding a purpose, basis, period, or format

purposes following specific terms

No Comments

No Known Activations