INDEX

Explanations

phrases indicating an intentional communication or note

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

__(/*!

-0.62

 jScrollPane

-0.55

bilirsiniz

-0.52

ेशा

-0.51

WarningLevel

-0.51

 totalité

-0.50

뀜

-0.50

 tudom

-0.50

 zelfs

-0.50

ophi

-0.49

POSITIVE LOGITS

 quick

1.73

 briefly

1.69

quick

1.57

 brief

1.55

 QUICK

1.45

Quick

1.43

 Quick

1.40

brief

1.35

QUICK

1.33

 quickly

1.32

Activations Density 0.417%

phrases indicating an intentional communication or note

No Comments

No Known Activations