INDEX

Explanations

references to geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

too

-0.46

 another

-0.43

 someone

-0.42

you

-0.42

BaseController

-0.39

 alone

-0.39

and

-0.39

Helper

-0.39

 must

-0.38

 something

-0.38

POSITIVE LOGITS

 autorytatywna

0.95

 Италијани

0.87

脚注の使い方

0.84

WireFormatLite

0.84

WriteTagHelper

0.83

Personensuche

0.81

 Meksiku

0.79

Vidite

0.79

pexpr

0.79

 للمعارف

0.78

Activations Density 0.068%

references to geographic locations

No Comments

No Known Activations