INDEX

Explanations

dates and years

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

 độc

-0.58

danke

-0.57



-0.56

 '\\;'

-0.56

chappement

-0.55

imarães

-0.52

தல்

-0.52

 Worten

-0.51

tagHelperRunner

-0.51

ből

-0.50

POSITIVE LOGITS

BeginContext

0.70

Tembelea

0.55

 actionPerformed

0.53

invokeLater

0.52

esModule

0.52

providedIn

0.51

onViewCreated

0.50

 consultato

0.50

obenz

0.48

 Seeder

0.47

Activations Density 0.120%

dates and years

No Comments

No Known Activations