INDEX

Explanations

terms related to authority and control over individuals or groups

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

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

Require

-0.53

[])

-0.52

će

-0.50

==",

-0.49

telah

-0.48

etheless

-0.48

zeba

-0.48

chend

-0.48

oneg

-0.45

δη

-0.45

POSITIVE LOGITS

 ProtoMessage

0.85

DockStyle

0.70

 nahilalakip

0.68

XmlAccessorType

0.67

 estekak

0.63

цездатний

0.61

få

0.57

 slide

0.56

bootstrapcdn

0.55

 bénéficier

0.55

Activations Density 0.210%

terms related to authority and control over individuals or groups

No Comments

No Known Activations