INDEX

Explanations

numerical values related to statistical measurements or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

OGND

-0.93

GEBURTSDATUM

-0.91

 ostavi

-0.89

----</

-0.86

يميديا

-0.86

Lähteet

-0.82

ModelAdmin

-0.80

ElementException

-0.80

 Italijani

-0.80

Hozzáférés

-0.79

POSITIVE LOGITS

ning

0.48

ValueStyle

0.47

ing

0.45

nja

0.44

 Settle

0.44

Rig

0.44

ッケージ

0.42

 Slee

0.42

pera

0.42

nje

0.41

Activations Density 0.551%

numerical values related to statistical measurements or observations

No Comments

No Known Activations