INDEX

Explanations

keywords and technical terminology related to scientific research and experimentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

mbggenerated

-0.56

 StringTokenizer

-0.53

terraform

-0.47

ंदीखरीदारी

-0.46

 porcelain

-0.46

GTCX

-0.46

BufferException

-0.45

 JsonResult

-0.44

httphttps

-0.44

Autoritní

-0.44

POSITIVE LOGITS

tagext

0.51

 unknownFields

0.43

而是

0.42

oneofs

0.40

LogFactory

0.38

ritation

0.38

енча

0.37

bootstrapcdn

0.37

Voci

0.36

 estacionamento

0.36

Activations Density 2.089%

keywords and technical terminology related to scientific research and experimentation

No Comments

No Known Activations