INDEX

Explanations

legal terms related to discrimination and judicial processes

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

fromnode

-0.62

tificate

-0.55

lobal

-0.53

ரி

-0.52

lesh

-0.49

 societies

-0.49

xã

-0.49

Comté

-0.48

bef

-0.47

lès

-0.46

POSITIVE LOGITS

 discrimination

0.95

 Discrimination

0.88

 discriminated

0.82

discrimination

0.78

 retaliation

0.74

 Equal

0.73

Protected

0.73

 protected

0.73

 harassment

0.71

 Protected

0.70

Activations Density 0.895%

legal terms related to discrimination and judicial processes

No Comments

No Known Activations