INDEX

Explanations

references to numbered volumes and issues in publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 كومونز

-0.86

Personensuche

-0.85

SequentialGroup

-0.84

 незавершена

-0.80

TypedDataSet

-0.74

 مشين

-0.73

findpost

-0.73

tagHelperRunner

-0.71

 الحره

-0.71

 виправивши

-0.69

POSITIVE LOGITS

 Sociale

0.58

 Exactly

0.51

 punggung

0.50

BagLayout

0.50

ărul

0.49

PAIGN

0.48

 wearable

0.48

 sweating

0.47

precise

0.47

№

0.47

Activations Density 0.099%

references to numbered volumes and issues in publications

No Comments

No Known Activations