INDEX

Explanations

words related to political events or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ธ์

-0.61

-0.59

σιμοποι

-0.53

upsi

-0.52

utuhkan

-0.51

lgari

-0.50

anasia

-0.49

דינה

-0.49

ruptedException

-0.49

 Anwendungen

-0.48

POSITIVE LOGITS

ReusableCell

0.98

تقاوى

0.97

Autoritní

0.92

出版年

0.83

 Wikimedijinoj

0.80

 XCTest

0.79

makeConstraints

0.78

 Italijanski

0.77

AndroidJUnit

0.77

 AssemblyCulture

0.76

Activations Density 1.396%

words related to political events or entities

No Comments

No Known Activations