INDEX

Explanations

numeric values and related scoring terms in a competitive context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

extAlignment

-0.60

verwijspagina

-0.55

 paramString

-0.54

 ujednoznacz

-0.53

 Mani

-0.51

rungsseite

-0.49

 jScrollPane

-0.47

Kaieteur

-0.47

homonymie

-0.47

География

-0.46

POSITIVE LOGITS

ysty

0.67

setVerticalGroup

0.63

yntaxException

0.63

 lienzo

0.60

bootstrapcdn

0.59

 ciasc

0.57

 chré

0.57

 الحره

0.56

 quæ

0.56

popularity

0.56

Activations Density 0.052%

numeric values and related scoring terms in a competitive context

No Comments

No Known Activations