INDEX

Explanations

instances of the word "most."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 cualquiera

-0.78

 veneta

-0.74

 ChromeDriver

-0.74

eraard

-0.73

 Ritter

-0.71

 Cluj

-0.70

capaian

-0.69

ORCID

-0.68

hagic

-0.67

 termica

-0.66

POSITIVE LOGITS

 most

1.24

most

0.98

 meest

0.95

MOST

0.94

 MOST

0.92

 best

0.90

Most

0.89

 Most

0.88

 najbardziej

0.84

 least

0.80

Activations Density 0.042%

instances of the word "most."

No Comments

No Known Activations