INDEX

Explanations

terms related to geographic locations and political territories

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

System

-1.15

 System

-1.06

 SYSTEM

-0.71

 system

-0.68

Syst

-0.66

SYSTEM

-0.59

はじめに

-0.57

 Syst

-0.57

 Systems

-0.56

 systeem

-0.56

POSITIVE LOGITS

exitRule

0.66

دانشنامهٔ

0.61

 ویکی‌پدیا

0.58

 zich

0.54

 sich

0.52

spesies

0.50

 noqa

0.50

SuccessListener

0.50

copyFrom

0.49

zość

0.48

Activations Density 0.106%

terms related to geographic locations and political territories

No Comments

No Known Activations