INDEX

Explanations

terms related to "activity" and its various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

 Италијани

-0.48

fjspx

-0.48

RepeatedField

-0.44

 pungkasnya

-0.43

EndInit

-0.41

invokeLater

-0.41

 Roskov

-0.40

SpringBootTest

-0.39

eqn

-0.38

kena

-0.38

POSITIVE LOGITS

 getActivity

0.60

 Activity

0.58

kegiatan

0.52

tonode

0.49

Activity

0.49

 BoxDecoration

0.48

 Activities

0.48

 participant

0.47

írit

0.46

Duty

0.44

Activations Density 0.112%

terms related to "activity" and its various forms

No Comments

No Known Activations