INDEX

Explanations

phrases related to summarizing actions and intentions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ására

-0.45

conceito

-0.43

すると

-0.39

伴

-0.37

ایا

-0.37

جوايز

-0.36

వు

-0.36

monial

-0.36

ритори

-0.36

LayoutStyle

-0.36

POSITIVE LOGITS

 focus

2.57

 Focus

2.28

focus

2.27

Focus

2.25

 focusing

2.22

 concentrate

2.17

Focusing

2.14

 focused

2.13

 focuses

2.13

 Focusing

2.13

Activations Density 0.338%

phrases related to summarizing actions and intentions in various contexts

No Comments

No Known Activations