INDEX

Explanations

terms and phrases related to updates or modifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Personendaten

-0.76

iverr

-0.69

 Khur

-0.65

sendFile

-0.62

Gim

-0.61

InitStructure

-0.61

Geh

-0.60

SneakyThrows

-0.59

 Cors

-0.59

POSITIVE LOGITS

 updater

1.36

 Updates

1.33

 Update

1.31

 update

1.29

UPD

1.26

 updates

1.25

 UPDATE

1.24

UpdateCommand

1.22

Update

1.21

updates

1.21

Activations Density 0.058%

terms and phrases related to updates or modifications

No Comments

No Known Activations