INDEX

Explanations

phrases that highlight inequalities or issues related to women's employment and physical capabilities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-1.15

 itſelf

-1.05

Efq

-1.03

berdayakan

-1.00

ſelf

-0.99

Portale

-0.98

 himſelf

-0.97

 Chriftian

-0.97

 uſed

-0.96

 Jefus

-0.95

POSITIVE LOGITS

fa

0.63

0.61

con

0.60

ha

0.60

si

0.60

hu

0.60

wo

0.59

le

0.57

Activations Density 0.262%

phrases that highlight inequalities or issues related to women's employment and physical capabilities

No Comments

No Known Activations