INDEX

Explanations

technical terms and data formats related to programming and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 می‌توان

-0.97

 می‌توانید

-0.84

 coö

-0.81

 می‌تواند

-0.74

 می‌گو

-0.66

‌ای

-0.66

 می‌ده

-0.65

 می‌دهد

-0.65

 می‌گوید

-0.64

 می‌شود

-0.63

POSITIVE LOGITS

 tambi

0.60

 dumne

0.50

sâ

0.50

 navide

0.45

 atrav

0.44

 zosta

0.44

 henkil

0.44

 Joaqu

0.41

 meille

0.40

 varandra

0.40

Activations Density 0.720%

technical terms and data formats related to programming and documentation

No Comments

No Known Activations