INDEX

Explanations

references to compensation and pay-related discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Admissions

-0.53

 Admissions

-0.50

Revenir

-0.49

Välislingid

-0.47

borrow

-0.47

 imprim

-0.46

tokio

-0.45

atists

-0.45

Raf

-0.45

liances

-0.44

POSITIVE LOGITS

 salary

1.77

pay

1.77

 wages

1.63

 salaries

1.62

 Salary

1.44

 wage

1.42

salary

1.40

 remuneration

1.37

Pay

1.37

pay

1.35

Activations Density 0.324%

references to compensation and pay-related discussions

No Comments

No Known Activations