INDEX

Explanations

names of characters and references to their roles in narratives

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

 budding

-0.35

 young

-0.33

eg

-0.33

 ай

-0.30

tserrat

-0.30

 abor

-0.30

 poto

-0.30

 girlfriend

-0.30

 preco

-0.30

bud

-0.30

POSITIVE LOGITS

 retired

0.98

 Elderly

0.98

👵

0.91

 elderly

0.88

👴

0.86

 Retired

0.85

retired

0.85

Retired

0.84

 ancianos

0.83

 retiring

0.82

Activations Density 0.621%

names of characters and references to their roles in narratives

No Comments

No Known Activations