INDEX

Explanations

references to sections and appendices in a document

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.67

-0.63

|')

-0.57

-0.56

-0.55

le

-0.54

Kam

-0.53

POSITIVE LOGITS

 Monfieur

0.98

 myſelf

0.96

 itſelf

0.95

 whoſe

0.93

Eſ

0.91

 iſt

0.91

 المعيارى

0.85

 Jefus

0.85

 faſt

0.85

 Anſ

0.84

Activations Density 0.434%

references to sections and appendices in a document

No Comments

No Known Activations