INDEX

Explanations

references to names, terminology, and concepts related to specific identifiers or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

aarrggbb

-0.81

 ThemeData

-0.66

initComponents

-0.60

CloseOperation

-0.57

 समीक्षक

-0.56

TargetException

-0.56

ⓘ

-0.55

enumii

-0.54

avance

-0.54

 <>",

-0.53

POSITIVE LOGITS

 ujednoznacz

0.63

__(/*!

0.54

 appunto

0.52

migrationBuilder

0.52

 mang

0.52

참고

0.50

 indeed

0.48

Przypisy

0.48

 livraison

0.47

 Booking

0.46

Activations Density 0.195%

references to names, terminology, and concepts related to specific identifiers or classifications

No Comments

No Known Activations