INDEX

Explanations

phrases related to the organization and sequencing of elements or cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ագրություններ

-0.47

ži

-0.44

 actif

-0.40

{})

-0.40

={<

-0.39

 intptr

-0.39

Void

-0.38

πε

-0.38

∬

-0.38

 Через

-0.38

POSITIVE LOGITS

 order

1.39

 chronological

1.30

 ordered

1.26

顺序

1.23

 Reihenfolge

1.21

순

1.19

 ORDER

1.17

 Order

1.16

 descending

1.16

 sequentially

1.15

Activations Density 0.584%

phrases related to the organization and sequencing of elements or cases

No Comments

No Known Activations