INDEX

Explanations

questions about understanding or making sense of concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 CreateTagHelper

-0.91

writeField

-0.76

 ISNI

-0.76

 EconPapers

-0.75

\{\\

-0.74

endphp

-0.73

 disambiguazione

-0.72

 Autorizaciones

-0.72

 }}"></

-0.65

Autoritní

-0.65

POSITIVE LOGITS

 magát

0.48

下载附件

0.46

 förstå

0.43

日閲覧

0.43

TacToe

0.43

big

0.42

Across

0.40

CompleteListener

0.40

 medesimo

0.39

 šed

0.39

Activations Density 0.091%

questions about understanding or making sense of concepts

No Comments

No Known Activations