INDEX

Explanations

references to employment status and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

didSet

-0.65

LEncoder

-0.63

])));

-0.62

 "..\..\..\

-0.59

 "}";

-0.58

]));

-0.57

Producers

-0.55

lccn

-0.55

 Commandant

-0.55

 "..\..\

-0.54

POSITIVE LOGITS

 employees

1.71

 employee

1.60

 employed

1.50

employees

1.43

employee

1.41

 employment

1.38

 Employees

1.36

Employees

1.32

Employee

1.30

 empleados

1.29

Activations Density 0.238%

references to employment status and classifications

No Comments

No Known Activations