INDEX

Explanations

references to monarchy and nobility, particularly related to kings and queens

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ագրություններ

-0.56

 venuto

-0.52

CloseOperation

-0.50

 hydrochloride

-0.49

ñales

-0.49

PyExc

-0.48

 spol

-0.48

<!--

-0.48

 evan

-0.48

ाउ

-0.47

POSITIVE LOGITS

 monarch

1.25

 kings

1.22

 royal

1.15

 monarchy

1.14

 Queen

1.13

 throne

1.12

 monarchs

1.12

 queen

1.11

 Kings

1.08

 king

1.07

Activations Density 0.240%

references to monarchy and nobility, particularly related to kings and queens

No Comments

No Known Activations