INDEX

Explanations

mentions of prime ministers and associated terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

schild

-0.56

 forState

-0.53

 Reiche

-0.52

 kasarigan

-0.48

 Permanente

-0.48

 nela

-0.47

скра

-0.47

#######

-0.47

illots

-0.46

 Exacts

-0.46

POSITIVE LOGITS

PRIME

0.94

 PRIME

0.86

 Prime

0.82

minister

0.78

 minister

0.78

 ministres

0.75

 facie

0.75

 Minister

0.73

Prime

0.73

prime

0.72

Activations Density 0.083%

mentions of prime ministers and associated terms

No Comments

No Known Activations