INDEX

Explanations

terms related to dependencies and relationships between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

SuspendLayout

-0.44

 Sommers

-0.44

 Xunit

-0.42

 Kader

-0.42

 offensi

-0.42

 Sucher

-0.41

 mosa

-0.40

 moza

-0.40

 Westen

-0.40

 inox

-0.39

POSITIVE LOGITS

tvguidetime

0.57

adeloupe

0.56

MessageTagHelper

0.51

#!/

0.50

bootstrapcdn

0.50

 AssemblyVersion

0.50

 nahilalakip

0.49

 fieldNum

0.48

saraba

0.48

tanleria

0.47

Activations Density 1.242%

terms related to dependencies and relationships between concepts

No Comments

No Known Activations