INDEX

Explanations

references to user account actions and authentication

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.93

 CreateTagHelper

-0.76

########.

-0.69

 BorderRadius

-0.68

 calendriers

-0.67

UnknownFields

-0.65

 MainAxisSize

-0.64

numerusform

-0.64

esgue

-0.63

DockStyle

-0.60

POSITIVE LOGITS

 login

1.03

 Login

0.92

登录

0.90

Login

0.88

 getLogin

0.87

login

0.80

ログイン

0.78

LOGIN

0.76

 logout

0.75

 sesión

0.75

Activations Density 0.180%

references to user account actions and authentication

No Comments

No Known Activations