INDEX

Explanations

references to processes or concepts involving "management" or activities that use "ment" suffixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Wikispecies

-0.65

jillo

-0.65

úly

-0.65

farin

-0.62

abytes

-0.62

Ruy

-0.62

 Jeffer

-0.61

 doccia

-0.61

avax

-0.60

뢰

-0.60

POSITIVE LOGITS

ment

2.88

ments

2.29

MENT

2.16

EMENT

1.89

 ment

1.88

MENTS

1.72

ement

1.65

メント

1.56

mento

1.50

मेंट

1.43

Activations Density 0.102%

references to processes or concepts involving "management" or activities that use "ment" suffixes

No Comments

No Known Activations