INDEX

Explanations

discussions related to LGBTQ+ representation and issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ardown

-0.58

UnknownFields

-0.51

amaha

-0.50

 Cune

-0.50

bronn

-0.50

 StringTokenizer

-0.48

 recul

-0.48

 Pelham

-0.45

jsdelivr

-0.45

település

-0.45

POSITIVE LOGITS

gay

2.03

 LGBT

1.80

 homosexual

1.80

 LGBTQ

1.79

gay

1.76

 gays

1.73

 lesbian

1.69

LGBT

1.66

Gay

1.65

 queer

1.62

Activations Density 0.226%

discussions related to LGBTQ+ representation and issues

No Comments

No Known Activations