INDEX

Explanations

technical terms and concepts related to data handling and error messages in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/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.33.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

NameInMap

-0.43

 <>",

-0.38

 berk

-0.36

Попис

-0.36

IndentedString

-0.35

 المف

-0.32

 hore

-0.32

 keratin

-0.32

bereits

-0.32

ceb

-0.32

POSITIVE LOGITS

np

0.65

 dtype

0.63

 array

0.63

 numpy

0.60

dtype

0.56

assertArray

0.55

 arrays

0.54

array

0.54

np

0.52

romyalgia

0.51

Activations Density 0.306%

technical terms and concepts related to data handling and error messages in programming

No Comments

No Known Activations