INDEX

Explanations

textual elements that highlight key points or important lists in the content

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

NewRow

-0.35

Collegamenti

-0.35

KURZBESCHREIBUNG

-0.35

ChildIndex

-0.34

getElementsBy

-0.33

 mapStateToProps

-0.32

Lietu

-0.31

kov

-0.31

皇

-0.31

ngOnDestroy

-0.30

POSITIVE LOGITS

ValueStyle

0.59

ronpa

0.54

ftagPool

0.53

 تضيفلها

0.51

ConstraintMaker

0.50

 CreateTagHelper

0.50

 BoxFit

0.49

enumii

0.48

 ujednoznacz

0.47

 收納

0.47

Activations Density 1.154%

textual elements that highlight key points or important lists in the content

No Comments

No Known Activations