INDEX

Explanations

proper nouns associated with specific locations or names in a narrative context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-0.75

aarrggbb

-0.64

istoitu

-0.63

 Meksiku

-0.59

LookAnd

-0.58

TOBER

-0.57

PathParam

-0.55

 Wiktionnaire

-0.53

())));

-0.53

 ioutil

-0.52

POSITIVE LOGITS

tableFuture

0.65

newArrayList

0.58

σθαι

0.56

 Préférences

0.55

Occasion

0.55

 AssemblyCompany

0.54

volles

0.52

étit

0.51

ècie

0.50

SuccessListener

0.50

Activations Density 0.327%

proper nouns associated with specific locations or names in a narrative context

No Comments

No Known Activations