INDEX

Explanations

geographical locations and their connections to specific services or features

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

AutoField

-0.51

multirow

-0.51

nonatomic

-0.47

 cheminée

-0.44

[](

-0.44

ทย

-0.44

 SafeMath

-0.43

eward

-0.42

ěk

-0.42

Twig

-0.42

POSITIVE LOGITS

 Dakota

0.96

Dakota

0.89

 Fargo

0.84

 Sioux

0.83

 Bismarck

0.82

Winnipeg

0.80

 Manitoba

0.79

 Winnipeg

0.76

 dakota

0.72

ND

0.68

Activations Density 0.143%

geographical locations and their connections to specific services or features

No Comments

No Known Activations