INDEX

Explanations

key terms and titles related to newsletters and updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 الرياضيه

-1.38

 gynhyrchwyd

-0.90

 صوتيه

-0.88

 esternos

-0.87

 HttpNotFound

-0.84

 Cytometry

-0.81

 AssemblyVersion

-0.80

 calendriers

-0.80

 ddelweddau

-0.80

 estekak

-0.80

POSITIVE LOGITS

UnusedPrivate

0.51

wide

0.48

west

0.42

Es

0.41

Sub

0.40

Alt

0.40

withstanding

0.40

Big

0.40

Bas

0.39

"?>

0.39

Activations Density 0.137%

key terms and titles related to newsletters and updates

No Comments

No Known Activations