INDEX

Explanations

references to users and user experience within a system or application

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

ValueStyle

-1.11

 Stopwatch

-0.83

PSM

-0.80

 combineReducers

-0.75

 defaultstate

-0.73

 AppComponent

-0.72

 ProductService

-0.71

HEC

-0.70

NDA

-0.70

CrossRef

-0.70

POSITIVE LOGITS

 users

1.90

 Users

1.88

 user

1.83

 User

1.71

Users

1.63

users

1.59

 USER

1.58

 pengguna

1.43

user

1.43

 USERS

1.42

Activations Density 0.050%

references to users and user experience within a system or application

No Comments

No Known Activations