INDEX

Explanations

terms related to legal and procedural contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 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

PrototypeOf

-0.46

 ujednoznacz

-0.44

 Audiodateien

-0.44

elemField

-0.41

/**

-0.40

Diweddarwch

-0.40

 nonatomic

-0.39

ConstraintMaker

-0.39

DebuggerNonUser

-0.38

omitempty

-0.37

POSITIVE LOGITS

ExtendWith

0.58

 miniaturka

0.45

 թվական

0.44

bootstrapcdn

0.44

 Putih

0.44

tanleria

0.43

 kaynağından

0.43

 zasi

0.42

 onBackPressed

0.41

skosten

0.41

Activations Density 2.322%

terms related to legal and procedural contexts

No Comments

No Known Activations