INDEX

Explanations

relationships and comparisons between entities or concepts

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 Wikime

-0.68

 disambiguazione

-0.68

randomUUID

-0.64

Tikang

-0.62

 Deputies

-0.57

clusal

-0.57

#+#

-0.56

uParam

-0.56

 Pompey

-0.56

DialogContent

-0.56

POSITIVE LOGITS

 Normdatei

0.55

Портали

0.54

Gweler

0.50

 annak

0.49

 those

0.48

 Paglinawan

0.47

 ویکی‌پدیا

0.46

责任编辑

0.46

Становништво

0.45

 azok

0.45

Activations Density 0.175%

relationships and comparisons between entities or concepts

No Comments

No Known Activations