INDEX

Explanations

references to military ranks, honors, and achievements

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

 désolés

-0.65

">//

-0.64

ритори

-0.55

 <<<<<<<<<<<<<<

-0.55

 trinh

-0.54

celotti

-0.51

 aspetti

-0.51

migrationBuilder

-0.50

 Mean

-0.50

uyasha

-0.49

POSITIVE LOGITS

 jspb

0.61

 ujednoznacz

0.60

>--}}

0.51

Olvid

0.50

 мәкал

0.50

Хро

0.49

 يتيمه

0.49

Referências

0.49

\]

0.48

"}";

0.48

Activations Density 0.268%

references to military ranks, honors, and achievements

No Comments

No Known Activations