INDEX

Explanations

technical terms and jargon related to GPU computing and programming

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-0.85

DotNetBar

-0.75

 initComponents

-0.74

WriteTagHelper

-0.72

saraba

-0.70

Edg

-0.69

CreateModel

-0.69

isk

-0.67

 Morm

-0.67

IBar

-0.67

POSITIVE LOGITS

uuuu

1.06

uu

1.00

uuu

0.99

ubus

0.88

uuuuu

0.86

UUUU

0.81

UU

0.81

ungeon

0.79

ZU

0.79

 utils

0.77

Activations Density 3.664%

technical terms and jargon related to GPU computing and programming

No Comments

No Known Activations