INDEX

Explanations

numerical indicators related to ranking or order, particularly involving ordinal numbers

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

er

-0.74

ed

-0.66

 Krie

-0.60

 ganas

-0.59

toHaveBeenCalled

-0.58

anneer

-0.57

aluz

-0.57

leş

-0.57

can

-0.57

apos

-0.56

POSITIVE LOGITS

 Tenth

1.05

tenth

1.05

sixth

1.04

 tenth

1.03

 fourth

1.00

teenth

0.99

 seventh

0.98

 fifth

0.98

 sixth

0.98

 Sixth

0.98

Activations Density 0.121%

numerical indicators related to ranking or order, particularly involving ordinal numbers

No Comments

No Known Activations