INDEX

Explanations

proper nouns, specifically names of people and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

</thead>

-0.59

 mong

-0.57

gg

-0.56

aries

-0.53

its

-0.52

ffine

-0.49

InstanceState

-0.49

zend

-0.47

enumi

-0.47

 Attention

-0.46

POSITIVE LOGITS

Autoritní

0.81

 intStringLen

0.74

ukses

0.74

queryInterface

0.72

iconque

0.72

tanleria

0.71

HasBeenSet

0.70

 Paglinawan

0.66

GeoNames

0.66

 feroit

0.66

Activations Density 0.192%

proper nouns, specifically names of people and organizations

No Comments

No Known Activations