INDEX

Explanations

references to measurement-related concepts and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ContentAsync

-0.78

 îna

-0.76

Portale

-0.70

 căr

-0.66

 izvē

-0.64

nicamente

-0.64

 către

-0.64

bif

-0.62

 obicei

-0.62

 antemano

-0.62

POSITIVE LOGITS

 measurement

2.30

 measurements

2.19

 Measurement

2.18

 Measurements

2.07

Measurement

2.02

 MEASUREMENT

1.99

 measuring

1.99

Measurements

1.93

 Measuring

1.92

measurement

1.91

Activations Density 0.099%

references to measurement-related concepts and terminology

No Comments

No Known Activations