INDEX

Explanations

terms related to suspension and folders

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Sui

-0.94

Vidite

-0.89

✨:

-0.86

 riva

-0.81

 becauſe

-0.79

 Picchu

-0.78

 myſelf

-0.78

γραφή

-0.78

 fufficient

-0.78

 canne

-0.76

POSITIVE LOGITS

 folders

0.88

 folder

0.77

Folders

0.75

rd

0.74

„

0.74

folders

0.74

FolderPath

0.73

}^{(

0.71

 uParam

0.71

EndGlobalSection

0.71

Activations Density 0.112%

terms related to suspension and folders

No Comments

No Known Activations