INDEX

Explanations

references to programming concepts and code-related instructions

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

 ब्रेकडाउन

-0.69

 arşivlendi

-0.67

 defaultstate

-0.63

makeText

-0.62

 ويكيميديا

-0.61

 nahilalakip

-0.60

Personensuche

-0.60

 betweenstory

-0.59

yntaxException

-0.58

 nakalista

-0.57

POSITIVE LOGITS

ky

0.39

Ten

0.34

 maybe

0.33

nan

0.32

 بور

0.31

 можешь

0.30

you

0.30

})->

0.30

omp

0.30

Activations Density 0.999%

references to programming concepts and code-related instructions

No Comments

No Known Activations