INDEX

Explanations

numerical values, particularly in the context of measurements or ratings

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

Rüyada

-0.79

 Autorisations

-0.63

 ویکی‌پدی

-0.58

 дописавши

-0.55

ValueStyle

-0.54

 EconPapers

-0.52

__).

-0.52

Personensuche

-0.50

hoeddwyd

-0.49

期刊论文

-0.48

POSITIVE LOGITS

İstinadlar

0.52

GenerationType

0.41

 presentation

0.40

ppt

0.39

AnimationsModule

0.38

 slides

0.35

chalk

0.34

 presentations

0.34

 Presentation

0.34

 pregunto

0.34

Activations Density 0.096%

numerical values, particularly in the context of measurements or ratings

No Comments

No Known Activations