INDEX

Explanations

words related to properties or attributes in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

GOTREF

-0.63

InjectMocks

-0.58

 BrowserModule

-0.57

 BigNumber

-0.54

ьаж

-0.53

ValueStyle

-0.53

कृ

-0.53

больше

-0.52

뢰

-0.51

 Pender

-0.50

POSITIVE LOGITS

 studios

0.88

 saites

0.69

 offices

0.69

properties

0.69

uxxxx

0.69

 apartments

0.67

Personendaten

0.67

 Properties

0.65

 Resource

0.64

rooms

0.63

Activations Density 0.148%

words related to properties or attributes in a technical context

No Comments

No Known Activations