INDEX

Explanations

references to various forms of measurement in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

⌈

-0.46

 Heil

-0.45

cephal

-0.44

раль

-0.43

 Kaufmann

-0.43

 wedi

-0.42

 pater

-0.42

Composite

-0.42

Ges

-0.42

Cumulative

-0.41

POSITIVE LOGITS

 measure

0.96

 measurement

0.93

 Measure

0.90

 Measurement

0.90

Measurement

0.87

 mesure

0.85

measure

0.83

 medida

0.83

MEASURE

0.82

Measure

0.81

Activations Density 0.269%

references to various forms of measurement in different contexts

No Comments

No Known Activations