INDEX

Explanations

mentions of professional titles and names, particularly in medical and legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 CreateTagHelper

-0.99

 للاسماء

-0.95

writeFieldEnd

-0.82

 cauſe

-0.69

 itſelf

-0.69

AnchorStyles

-0.69

 nonUne

-0.65

ReusableCell

-0.64

Espèce

-0.64

FXML

-0.64

POSITIVE LOGITS

 通販

0.51

 Vikipedi

0.48

PhysRev

0.48

izr

0.46

Notae

0.44

íncia

0.42

...@

0.42

PhysRevD

0.40

 Haush

0.40

 població

0.39

Activations Density 0.163%

mentions of professional titles and names, particularly in medical and legal contexts

No Comments

No Known Activations