INDEX

Explanations

numerical ratings or scores associated with evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 disambiguazione

-0.58

folio

-0.50

orianCalendar

-0.49

 لينك

-0.48

StoryboardSegue

-0.47

parsedMessage

-0.47

FXML

-0.47

ference

-0.46

 للمعارف

-0.45

detta

-0.45

POSITIVE LOGITS

 rating

0.59

Rating

0.50

★★★★★

0.48

 classificação

0.48

 ratings

0.47

 Rating

0.46

⭐⭐⭐⭐

0.46

 mérit

0.45

 ★★★★★

0.44

 overall

0.44

Activations Density 0.181%

numerical ratings or scores associated with evaluations

No Comments

No Known Activations