INDEX

Explanations

numerical and bibliographic references related to research citations and documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

存于互联网档案馆

-0.78

 <=",

-0.74

IntoConstraints

-0.72

تقاوى

-0.67

 CreateTagHelper

-0.65

 препратки

-0.63

клопе

-0.63

ContentAlignment

-0.62

ngdoc

-0.62

الإنجليزية

-0.61

POSITIVE LOGITS

тельстве

0.58

thâu

0.54

WithIOException

0.53

jemahan

0.53

bare

0.51

Pyx

0.51

indakan

0.51

 infatti

0.49

urably

0.49

 Organisationen

0.48

Activations Density 0.068%

numerical and bibliographic references related to research citations and documents

No Comments

No Known Activations