INDEX

Explanations

instances of the word "login" and its variations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 AssemblyCulture

-0.98

ValueStyle

-0.98

 autorytatywna

-0.97

 CreateTagHelper

-0.95

CodeAnalysis

-0.92

newArrayList

-0.91

 getRule

-0.88

ImageContext

-0.88

IsContent

-0.87

KommentareTeilen

-0.85

POSITIVE LOGITS

login

1.56

 LOGIN

1.55

 login

1.55

LOGIN

1.51

Login

1.50

 Login

1.50

 getLogin

1.37

getLogin

1.33

setLogin

1.20

 登录

1.06

Activations Density 0.047%

instances of the word "login" and its variations within the text

No Comments

No Known Activations