INDEX

Explanations

phrases related to intent and awareness of consequences

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

celle

-0.57

uticos

-0.54

 Elective

-0.52

BAG

-0.52

ợp

-0.52

 Ensemble

-0.52

Bom

-0.51

 Aircraft

-0.51

 pinta

-0.51

ñana

-0.50

POSITIVE LOGITS

rungsseite

0.81

Geplaatst

0.69

Personendaten

0.69

 lenker

0.66

AnimationsModule

0.65

RetentionPolicy

0.64

BindingResult

0.63

EnableWeb

0.57

bootstrapcdn

0.55

 հղումներ

0.55

Activations Density 0.411%

phrases related to intent and awareness of consequences

No Comments

No Known Activations