INDEX

Explanations

technical terms and metrics related to LiDAR technology and its applications

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

 Raim

-0.88

oporosis

-0.88

.--

-0.87

gridx

-0.86

 Aras

-0.85

Tul

-0.85

AndEndTag

-0.84

Демографія

-0.84

 Deepak

-0.83

Yag

-0.83

POSITIVE LOGITS

Li

0.90

li

0.86

Li

0.77

livery

0.76

lister

0.76

EqualsAnd

0.73

LI

0.73

Rena

0.73

 Lilly

0.72

 MORGAN

0.72

Activations Density 1.768%

technical terms and metrics related to LiDAR technology and its applications

No Comments

No Known Activations