INDEX

Explanations

references to methods and materials used in research articles

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

 than

-0.53

ant

-0.51

-0.47

nt

-0.44

ones

-0.44

or

-0.42

ní

-0.41

ب

-0.40

ent

-0.40

POSITIVE LOGITS

DockStyle

1.15

 المعيارى

1.01

 typelib

0.96

DeleteBehavior

0.94

EndGlobalSection

0.92

 فريبيس

0.91

ISupport

0.87

MLLoader

0.81

ollectionView

0.81

awtextra

0.79

Activations Density 0.711%

references to methods and materials used in research articles

No Comments

No Known Activations