INDEX

Explanations

references to identification documents or IDs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 kilometre

-0.65

Fibre

-0.64

"/>

-0.61

 fibre

-0.60

 Fibre

-0.59

 fibres

-0.58

zelle

-0.58

AddHtmlAttribute

-0.58

 gameObject

-0.57

 marvellous

-0.56

POSITIVE LOGITS

ID

0.93

IDs

0.75

__':

0.73

__":

0.71

 fhew

0.69

__':

0.67

__":

0.64

XmlAccessorType

0.60

 medal

0.60

EnableWeb

0.60

Activations Density 0.082%

references to identification documents or IDs

No Comments

No Known Activations