INDEX

Explanations

references to classes in programming or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 <<<<<<<<<<<<<<

-0.71

 fotografico

-0.53

 légiti

-0.53

Locally

-0.51

 pips

-0.51

 Practically

-0.51

 élu

-0.50

ciąż

-0.50

 územ

-0.49

 ilha

-0.49

POSITIVE LOGITS

 class

0.65

 Class

0.64

webElementXpaths

0.62

Class

0.61

getClass

0.60

clazz

0.59

 multer

0.59

PointerException

0.58

>>()

0.58

]=-

0.56

Activations Density 0.102%

references to classes in programming or coding contexts

No Comments

No Known Activations