INDEX

Explanations

expressions of negative sentiment or losses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 resourceCulture

-0.74

Демографія

-0.68

XmlAccessType

-0.63

parsedMessage

-0.57

Espèce

-0.56

archiviato

-0.54

råd

-0.54

 partea

-0.54

 îns

-0.53

 illustrazione

-0.53

POSITIVE LOGITS

 AssemblyCulture

0.62

則是

0.58

 FetchType

0.58

 esternos

0.57

則

0.52

таратура

0.51

+#+

0.51

 situe

0.51

']));

0.50

则是

0.50

Activations Density 1.142%

expressions of negative sentiment or losses

No Comments

No Known Activations