INDEX

Explanations

references to U.S. locations and technical terms related to signals and processing in a computational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Chham

-0.78

 Theſe

-0.70

<",

-0.68

/\.

-0.62

uxxxx

-0.60

 igång

-0.58

 Độ

-0.58

 myſelf

-0.58

ductory

-0.57

 dandy

-0.56

POSITIVE LOGITS

GEBURTSDATUM

0.77

 autorytatywna

0.52

 متعلقه

0.51

MessageOf

0.51

protoimpl

0.45

 nahilalakip

0.45

BarStyle

0.44

发表于

0.44

Tembelea

0.44

SuccessListener

0.43

Activations Density 4.537%

references to U.S. locations and technical terms related to signals and processing in a computational context

No Comments

No Known Activations