INDEX

Explanations

references to figures, graphs, or illustrations in the document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 chế

-0.56

fatalError

-0.54

]=="

-0.54

◤

-0.50

 Geraadpleegd

-0.50

le

-0.49

van

-0.49

onato

-0.48

ditto

-0.48

 numerus

-0.48

POSITIVE LOGITS

 الحره

0.89

 myſelf

0.87

 InputDecoration

0.86

IsContent

0.81

 himſelf

0.76

 ſche

0.75

 itſelf

0.72

 Majefty

0.70

 greateſt

0.70

 Cæsar

0.70

Activations Density 0.409%

references to figures, graphs, or illustrations in the document

No Comments

No Known Activations