INDEX

Explanations

references to institutions, funding, and authorship in academic or research contexts

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

 rozwo

-0.73

 محفوظة

-0.73

 podró

-0.71

edip

-0.71

oarece

-0.69

 sobą

-0.69

 Monfieur

-0.69

 mieście

-0.68

 Verk

-0.66

 słoń

-0.65

POSITIVE LOGITS

 Pologne

0.92

Marcin

0.91

 Marcin

0.88

 Polish

0.86

Polish

0.82

Poland

0.82

 Poland

0.81

Przypisy

0.79

 Lewandowski

0.79

 Witcher

0.79

Activations Density 0.135%

references to institutions, funding, and authorship in academic or research contexts

No Comments

No Known Activations