INDEX

Explanations

the beginning of a document or a new section

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

 Baillargeon

-0.81

urman

-0.64

canton

-0.63

 skär

-0.61

 prose

-0.59

 SEVENTH

-0.58

präche

-0.58

akaian

-0.58

 Prose

-0.57

 dépens

-0.57

POSITIVE LOGITS

HttpServlet

1.56

 HttpServlet

0.89

 transfieras

0.82

 propOrder

0.76

 createState

0.76

########.

0.73

XmlAccessorType

0.71

providedIn

0.71

 defStyleAttr

0.62

TargetException

0.61

Activations Density 0.022%

the beginning of a document or a new section

No Comments

No Known Activations