INDEX

Explanations

names of individuals and entities, particularly in legal or academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 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

WEBPACK

-0.58

aneers

-0.49

manteau

-0.48

 jScrollPane

-0.48

ssf

-0.46

/**

-0.45

ViewFeatures

-0.45

掾

-0.45

 madura

-0.45

󠁢

-0.44

POSITIVE LOGITS

LabelTagHelper

0.59

zzleHttp

0.58

########.

0.56

 autorytatywna

0.54

webElementXpaths

0.51

+#+#

0.50

WithIOException

0.50

XmlEnum

0.49

makeConstraints

0.48

 DbSet

0.44

Activations Density 0.791%

names of individuals and entities, particularly in legal or academic contexts

No Comments

No Known Activations