INDEX

Explanations

error handling in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 нале

-0.49

DialogTitle

-0.48

 Werth

-0.46

onomía

-0.45

byter

-0.43

 courses

-0.42

 sang

-0.42

SCE

-0.41

perti

-0.41

 granddaughter

-0.40

POSITIVE LOGITS

webElementXpaths

0.84

FXMLLoader

0.82

 ujednoznacz

0.66

basicConfig

0.65

 uska

0.64

 wireType

0.64

kuuta

0.63

脚注の使い方

0.63

Superview

0.63

 ISNI

0.62

Activations Density 0.116%

error handling in code

No Comments

No Known Activations