INDEX

Explanations

statistics related to gender roles and perceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 متعلقه

-0.63

umab

-0.48

ępnie

-0.47

 celebrado

-0.46

žin

-0.46

 bilde

-0.46

 Geschmack

-0.45

bosis

-0.44

ocino

-0.44

 بيها

-0.44

POSITIVE LOGITS

 chores

1.58

 housework

1.53

 tasks

1.38

 Tasks

1.27

 errands

1.22

 laundry

1.19

 task

1.18

tasks

1.15

 household

1.13

Tasks

1.13

Activations Density 0.371%

statistics related to gender roles and perceptions

No Comments

No Known Activations