INDEX

Explanations

references to rankings or recognition of organizations and their achievements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntoConstraints

-0.69

sizeCache

-0.66

SharedCtor

-0.64

ArgsConstructor

-0.63

ThroughAttribute

-0.62

 createContext

-0.57

 chi̍t

-0.57

sweise

-0.54

 resourceCulture

-0.53

 AssemblyCulture

-0.52

POSITIVE LOGITS

TagMode

0.65

bootstrapcdn

0.52

 giornal

0.51

 desbloquear

0.49

 aanv

0.48

åp

0.47

 veder

0.47

 verrou

0.47

 estekak

0.47

 utvik

0.46

Activations Density 0.339%

references to rankings or recognition of organizations and their achievements

No Comments

No Known Activations