INDEX

Explanations

linguistic terms and references related to language and dialects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 анг

-0.52

 Koreans

-0.51

 engelsk

-0.49

日本人

-0.49

 anglaise

-0.49

 englisch

-0.48

gdala

-0.47

NameInMap

-0.47

 Englishman

-0.47

 externi

-0.47

POSITIVE LOGITS

 dialect

0.84

 dialects

0.77

 Dial

0.66

dialect

0.65

 Standard

0.56

Dialect

0.55

 dial

0.54

 standard

0.54

 variant

0.54

 spoken

0.54

Activations Density 0.258%

linguistic terms and references related to language and dialects

No Comments

No Known Activations