INDEX

Explanations

references to unisex bathrooms and related gender-neutral concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

tvguidetime

-0.68

RegressionTest

-0.54

orsese

-0.52

 aéri

-0.51

 cabrio

-0.51

 دیکھیے

-0.51

 religieuses

-0.51

 quelcon

-0.50

 saurait

-0.49

ništ

-0.49

POSITIVE LOGITS

 locker

1.44

 restrooms

1.41

 restroom

1.38

 toilets

1.33

 dressing

1.31

 toilet

1.29

 lockers

1.23

 bathrooms

1.23

 wash

1.17

 bathroom

1.16

Activations Density 0.153%

references to unisex bathrooms and related gender-neutral concepts

No Comments

No Known Activations