INDEX

Explanations

specific model names or identifiers related to vehicles and automotive specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ondissement

-0.67

pidou

-0.60

newspaper

-0.57

ciutto

-0.56

Repost

-0.55

Referencer

-0.55

 mực

-0.54

ponses

-0.54

leih

-0.53

LookAnd

-0.53

POSITIVE LOGITS

 serisi

0.66

 Series

0.65

 series

0.61

 SERIES

0.57

 modellen

0.55

 serien

0.52

Series

0.52

 série

0.51

 serii

0.50

 serie

0.49

Activations Density 0.339%

specific model names or identifiers related to vehicles and automotive specifications

No Comments

No Known Activations