INDEX

Explanations

mentions of authorship and versioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

UnsafeEnabled

-0.60

InputTagHelper

-0.54

manship

-0.53

bootstrapcdn

-0.53

 Arro

-0.52

FormTagHelper

-0.52

бург

-0.52

GeneratedMessage

-0.50

HtmlAttribute

-0.50

!("{

-0.47

POSITIVE LOGITS

author

0.97

 kasarigan

0.69

 Assignee

0.65

 createdBy

0.64

defendant

0.63

 littéraire

0.62

 author

0.61

Lähteet

0.60

 AssemblyCompany

0.59

//

0.58

Activations Density 0.036%

mentions of authorship and versioning

No Comments

No Known Activations