INDEX

Explanations

coordinates or mathematical terms related to sequences and functions

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

 surla

-0.68

SpringBootTest

-0.66

readFileSync

-0.61

 trajets

-0.60

 useStyles

-0.58

BindView

-0.55

WebVitals

-0.54

titleMargin

-0.54

 BoxFit

-0.53

]-->

-0.52

POSITIVE LOGITS

fjspx

0.60

 kasarigan

0.58

 enfans

0.54

yntaxException

0.54

oredCriteria

0.53

 विश्वसनीयता

0.53

Manbalar

0.50

 Romains

0.49

NSIndexPath

0.47

onActivityResult

0.47

Activations Density 2.732%

coordinates or mathematical terms related to sequences and functions

No Comments

No Known Activations