INDEX

Explanations

terms related to computer networking

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

casio

-0.52

rimo

-0.51

ainville

-0.51

 suivantes

-0.50

airbnb

-0.48

 paes

-0.48

 subir

-0.47

ISODE

-0.47

tifies

-0.46

asters

-0.46

POSITIVE LOGITS

Хьажоргаш

0.72

 '\\;'

0.71

 jspb

0.64

DotNetBar

0.63

 RIPRODUZIONE

0.62

AccessorTable

0.60

 AllAfrica

0.59

.~(\

0.58

 سكانية

0.58

MemoryWarning

0.58

Activations Density 0.935%

terms related to computer networking

No Comments

No Known Activations