INDEX

Explanations

specific product names and their features

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

#+#

-0.55

出版年

-0.49

 known

-0.39

 Schein

-0.37

 under

-0.35

 struck

-0.35

copio

-0.34

 poffible

-0.34

 Sche

-0.34

 moſt

-0.34

POSITIVE LOGITS

SequentialGroup

0.65

 propOrder

0.57

 CanadaChoose

0.56

AntiForgeryToken

0.52

__":

0.48

__':

0.48

__':

0.48

 useRef

0.47

ValueStyle

0.47

FunctionFlags

0.46

Activations Density 0.163%

specific product names and their features

No Comments

No Known Activations