INDEX

Explanations

terms related to software features or applications

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

انيف

-0.88

ValueStyle

-0.86

 cherchés

-0.78

 picioare

-0.78

 maș

-0.74

Gambas

-0.73

 endforeach

-0.73

 înal

-0.72

 Waray

-0.72

 noDo

-0.72

POSITIVE LOGITS

 Romanian

0.72

Romania

0.66

 Romania

0.65

änien

0.62

 թվական

0.62

 Bucharest

0.57

 Dacia

0.49

Ghe

0.49

 Cluj

0.46

 تضيفلها

0.46

Activations Density 0.106%

terms related to software features or applications

No Comments

No Known Activations