INDEX

Explanations

elements related to specific scientific or technical standards and classifications

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

 avoient

-0.76

 pouvoit

-0.69

 reaſon

-0.62

 feroit

-0.61

 OBITUARY

-0.59

 étoit

-0.58

 Theſe

-0.57

 auroit

-0.57

createCanvas

-0.56

 berjudul

-0.56

POSITIVE LOGITS

EndContext

0.78

StructEnd

0.78

󠁿

0.74

 pinulongan

0.71

μβρίου

0.70

WRENCE

0.60

ImageContext

0.59

<>();

0.56

Portail

0.56

Hauptartikel

0.56

Activations Density 6.600%

elements related to specific scientific or technical standards and classifications

No Comments

No Known Activations