INDEX

Explanations

terms related to justification and legality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

fjspx

-1.03

 ThemeData

-0.71

ंदीखरीदारी

-0.70

IonicModule

-0.70

 MaterialApp

-0.68

usermodel

-0.67

 CreateTagHelper

-0.67

IUrlHelper

-0.67

pshot

-0.65

udesta

-0.65

POSITIVE LOGITS

 légitime

1.06

 justified

1.02

 justification

0.94

 justifies

0.87

 legitimate

0.86

 justi

0.86

 légiti

0.86

 justify

0.84

 legitimacy

0.81

 rightfully

0.81

Activations Density 0.412%

terms related to justification and legality

No Comments

No Known Activations