INDEX

Explanations

technical terminology and components related to programming and system signals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 SDLK

-0.55

 comerciais

-0.52

 būtų

-0.48

 createState

-0.48



-0.48

NUMX

-0.46

 colspan

-0.46

prox

-0.46

":[{

-0.45

 veau

-0.45

POSITIVE LOGITS

parsedMessage

1.07

хьтан

1.03

transQ

0.95

contentLoaded

0.95

 '\\;'

0.95

EndGlobalSection

0.93

OGND

0.90

LookAnd

0.89

Aholisi

0.88

ItemBackground

0.87

Activations Density 0.102%

technical terminology and components related to programming and system signals

No Comments

No Known Activations