INDEX

Explanations

phrases related to evaluation and measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

and

-0.82

MigrationBuilder

-0.53

 geslacht

-0.51

<?

-0.49

Personendaten

-0.46

 denk

-0.44

Hentet

-0.44

знание

-0.42

guien

-0.42

性和

-0.41

POSITIVE LOGITS

 informée

0.70

abestanden

0.66

Портал

0.64

parsedMessage

0.62

 therefor

0.62

toMatchSnapshot

0.61

何より

0.60

PointerException

0.60

xase

0.59

PerformLayout

0.58

Activations Density 0.479%

phrases related to evaluation and measurement

No Comments

No Known Activations