INDEX

Explanations

references to templates within the document

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

/**

-0.67

DllImport

-0.57

writeFieldEnd

-0.56

Tikang

-0.55

原始内容存档于

-0.52



-0.51

-/**

-0.49

 Bioaccumulative

-0.49

NoSuchAlgorithm

-0.49

Portail

-0.48

POSITIVE LOGITS

tpl

1.83

tpl

1.20

Tpl

0.86

TPL

0.75

smarty

0.74

 Smarty

0.53

 template

0.50

 Template

0.49

templateUrl

0.48

tmpl

0.47

Activations Density 0.000%

references to templates within the document

No Comments

No Known Activations