INDEX

Explanations

references to specific locations and transportation infrastructure

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

évaluateur

-0.81

httphttps

-0.69

 estekak

-0.68

 Tuba

-0.65

 שוליים

-0.64

 Vanuatu

-0.62

 Agamemnon

-0.60

epiece

-0.58

 CreateTagHelper

-0.57

 Malibu

-0.57

POSITIVE LOGITS

 Northumberland

0.83

 Newcastle

0.73

 Nottingham

0.73

 Peterborough

0.68

Nottingham

0.66

Newcastle

0.66

 Notting

0.65

 Thü

0.60

 Recife

0.59

 Trent

0.57

Activations Density 0.215%

references to specific locations and transportation infrastructure

No Comments

No Known Activations