INDEX

Explanations

words associated with generosity and nobility

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 nemesis

-0.58

vedades

-0.52

 referenties

-0.49

 idyl

-0.48

 unbear

-0.48

 Suiza

-0.47

 Gallimard

-0.47

 heartbreak

-0.46

 Vergangenheit

-0.46

 enfance

-0.46

POSITIVE LOGITS

 honorable

1.16

 dignified

1.13

 honourable

1.10

 noble

1.09

noble

1.02

 Elegant

0.96

Elegant

0.92

 generous

0.89

 elegant

0.88

 Honorable

0.86

Activations Density 0.187%

words associated with generosity and nobility

No Comments

No Known Activations