INDEX

Explanations

references to "other" people or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

marginHorizontal

-0.67

 Tyres

-0.59

两者

-0.59

 Harare

-0.58

 itinéraires

-0.57

ρας

-0.57

alignSelf

-0.57

AnchorStyles

-0.56

paddingVertical

-0.56

 alike

-0.55

POSITIVE LOGITS

 potato

0.88

 potatoes

0.85

 onion

0.71

 nakalista

0.66

出版年

0.65

internalType

0.65

 للاسماء

0.64

 ***!

0.64

Билгалдахарш

0.63

 Onion

0.61

Activations Density 0.108%

references to "other" people or entities

No Comments

No Known Activations