INDEX

Explanations

terms related to authority and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-1.71

an

-1.48

 another

-1.18

 seorang

-1.11

 eine

-1.09

一个

-1.06

 sebuah

-1.06

 einem

-1.02

 একটি

-1.00

 एक

-0.98

POSITIVE LOGITS

 poszczegól

1.02

 للمعارف

1.01

zczegól

0.98

 FetchType

0.95

ArrowToggle

0.95

رشف

0.95

出版年

0.94

 nahilalakip

0.93

IVEREF

0.92

 <<<<<<<<<<<<<<

0.91

Activations Density 1.111%

terms related to authority and governance

No Comments

No Known Activations