INDEX

Explanations

phrases related to location and context within texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 Ente

-0.45

 externes

-0.40

posables

-0.39

eningrad

-0.39

 הנ

-0.38

 Willen

-0.38

istán

-0.38

ument

-0.37

되

-0.37

metr

-0.37

POSITIVE LOGITS

findpost

1.01

脚注の使い方

0.87

 متعلقه

0.86

новниш

0.83

AddAttribute

0.82

 EconPapers

0.80

ViewFeatures

0.78

contentLoaded

0.77

zielle

0.74

casm

0.73

Activations Density 0.151%

phrases related to location and context within texts

No Comments

No Known Activations