INDEX

Explanations

questions and inquiries related to specific information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

cshtml

-0.71

허

-0.60

 surla

-0.59

Lup

-0.56

Jeografia

-0.55

)))));

-0.52

))^

-0.52

Lup

-0.52

Rè

-0.52

JspWriter

-0.52

POSITIVE LOGITS

ContentAlignment

0.70

saraba

0.57

Étymologie

0.54

VersionUID

0.54

InSection

0.54

 DbSet

0.52

QtWidgets

0.52

RunAsync

0.51

vnode

0.51

AtIndexPath

0.50

Activations Density 0.185%

questions and inquiries related to specific information

No Comments

No Known Activations