INDEX

Explanations

general references to various items or topics, particularly those categorized as 'stuff'

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

Datuak

-0.82

getCmp

-0.75

"{{

-0.74

MenuView

-0.69

 Lindley

-0.68

 Harms

-0.67

 OpenStreetMap

-0.66

 jengibre

-0.65

liferay

-0.64

 Centra

-0.63

POSITIVE LOGITS

 stuff

2.51

 Stuff

2.35

Stuff

2.21

 STUFF

2.16

stuff

2.10

 stuffs

1.80

 stuffing

1.22

 crap

1.19

stuffs

1.17

 junk

1.13

Activations Density 0.081%

general references to various items or topics, particularly those categorized as 'stuff'

No Comments

No Known Activations