INDEX

Explanations

numbers that indicate significant figures or data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 utafitiHapana

-0.75

RenderAtEndOf

-0.59

MLLoader

-0.58

Бахар

-0.52

HtmlAttribute

-0.52

npmjs

-0.52

 desideri

-0.51

 Pequ

-0.50

 CreateTagHelper

-0.47

setItems

-0.47

POSITIVE LOGITS

 mendatang

0.47

mobileqq

0.40

BASEPATH

0.35

หลวง

0.35

WebServlet

0.34

dawnictwo

0.34

 soir

0.34

 olympique

0.33

vician

0.33

 lehe

0.32

Activations Density 0.046%

numbers that indicate significant figures or data points

No Comments

No Known Activations