INDEX

Explanations

terms related to statistical analysis or results in research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 vastaan

-0.61

 titolata

-0.60

 favoris

-0.60

 waard

-0.59

 umana

-0.59

 sauvages

-0.58

 bucal

-0.58

yakit

-0.56

 goederen

-0.56

 hvě

-0.56

POSITIVE LOGITS

 millennial

1.18

 millennials

1.10

 young

1.08

 Millennials

1.01

 college

0.98

 middle

0.97

 parents

0.94

young

0.92

 younger

0.89

 parent

0.88

Activations Density 0.453%

terms related to statistical analysis or results in research studies

No Comments

No Known Activations