INDEX

Explanations

derogatory terms and expressions related to individuals or groups in a negative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 Superhost

-0.40

ClientRect

-0.40

Personendaten

-0.39

 considerable

-0.38

 Dalio

-0.37

紆

-0.36

depar

-0.36

 damen

-0.36

 unes

-0.36

jspb

-0.36

POSITIVE LOGITS

 basura

0.60

 stupid

0.59

 idiotic

0.58

 scum

0.56

 lixo

0.55

 crap

0.55

 coward

0.55

 waste

0.55

 idiot

0.54

 worthless

0.54

Activations Density 0.694%

derogatory terms and expressions related to individuals or groups in a negative context

No Comments

No Known Activations