INDEX

Explanations

phrases indicating relationships or connections between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

kä

-0.48

Esa

-0.47

omyces

-0.47

hadi

-0.46

stā

-0.46

ölt

-0.43

 berhubungan

-0.42

 læng

-0.42

odotus

-0.41

obis

-0.41

POSITIVE LOGITS

IsMutable

1.24

IndentedString

1.22

 AssemblyCulture

1.14

原始内容存档于

1.08

LookAnd

1.07

GEBURTSDATUM

1.07

Portale

1.02

WebVitals

1.02

ernalia

1.01

 IBOutlet

1.01

Activations Density 0.659%

phrases indicating relationships or connections between entities

No Comments

No Known Activations